Showing 1–50 of 75 results for author: Ramamoorthi, R

ArtLang: Structured Language-to-Kinematics Grounding for Articulated 3D Actuation

Authors: Sylvia Yuan, Dan Wang, Ravi Ramamoorthi, Xinrui Cui

Abstract: Articulated-object reconstructions recover explicit geometry and kinematics, but their parts often remain semantically anonymous and must be controlled through part indices and numerical joint parameters. We present ArtLang, a framework for open-vocabulary language control of persistent reconstructed articulated assets. ArtLang represents an asset as a semantic-kinematic articulation graph and aug… ▽ More Articulated-object reconstructions recover explicit geometry and kinematics, but their parts often remain semantically anonymous and must be controlled through part indices and numerical joint parameters. We present ArtLang, a framework for open-vocabulary language control of persistent reconstructed articulated assets. ArtLang represents an asset as a semantic-kinematic articulation graph and augments its surface with language features and graph-constrained motion. Open-vocabulary proposals are bound to reconstructed parts while allowing uncertain parts to remain unnamed. A typed parser converts a command into a directive graph containing referring expressions, actions, magnitudes, reference frames, and relations. We then solve a global graph-to-graph grounding problem that jointly reasons about semantic, spatial, relational, and kinematic compatibility, with support for null assignments and abstention under ambiguity. Accepted directives are converted into continuous joint targets within the observed motion range and executed through forward kinematics. Experiments on synthetic reconstructions, mesh-based assets, and real captures demonstrate reliable language grounding and continuous articulated control across repeated parts, spatial references, relational commands, and ambiguous instructions. △ Less

Submitted 15 August, 2026; originally announced August 2026.

RGBX-Next: Towards Realistic Generative Rendering from G-Buffers

Authors: Zheng Zeng, Marco Salvi, Lifan Wu, Jan Novák, Daqi Lin, Saeed Hadadan, Yichen Sheng, Robert Pottorff, Shiqiu Liu, Ravi Ramamoorthi, Ling-Qi Yan, Miloš Hašan

Abstract: Diffusion models have achieved impressive results in image, video, and streaming generation. However, compared to traditional 3D rendering, they still lack precise control over the generated output. We believe a viable path forward is to use generative models as learned renderers conditioned on traditionally rendered G-buffers. We introduce RGBX-Next, a unified generative framework for forward and… ▽ More Diffusion models have achieved impressive results in image, video, and streaming generation. However, compared to traditional 3D rendering, they still lack precise control over the generated output. We believe a viable path forward is to use generative models as learned renderers conditioned on traditionally rendered G-buffers. We introduce RGBX-Next, a unified generative framework for forward and inverse rendering, which allows estimating G-buffers from images, videos, and streams, and rendering realistic images, videos, and streams from G-buffers. Our key contribution is a general recipe for finetuning diffusion transformer (DiT) models into generative forward and inverse renderers. We show that the resulting models achieve high quality in both realistic generative rendering and intrinsic decomposition. We will make all our models publicly available. We believe that the design principles presented in this paper will benefit future research on controllable generative forward and inverse rendering. △ Less

Submitted 13 August, 2026; originally announced August 2026.

ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics

Authors: Sylvia Yuan, Dan Wang, Ravi Ramamoorthi, Xinrui Cui

Abstract: We present ArtMesh, a mesh-native method for reconstructing articulated objects explicitly as connected triangle meshes with per-part rigid motion from multi-view images in start and end states. Existing 3D Gaussian Splatting pipelines for articulated reconstruction inherit the unstructured point-based geometry of their splatting base, which provides no surface topology for reasoning about part bo… ▽ More We present ArtMesh, a mesh-native method for reconstructing articulated objects explicitly as connected triangle meshes with per-part rigid motion from multi-view images in start and end states. Existing 3D Gaussian Splatting pipelines for articulated reconstruction inherit the unstructured point-based geometry of their splatting base, which provides no surface topology for reasoning about part boundaries or enforcing motion consistency along the object's connectivity. ArtMesh instead builds on a mesh-based differentiable rendering backbone, enabling part-aware dynamics to act directly on the structured topology. To make the topology compatible with articulation, we introduce part-aware restricted Delaunay remeshing, producing connected submeshes whose triangles do not cross semantic part boundaries. The dynamic mesh field then optimizes articulation using bidirectional Vertex-wise Motion Consistency on transported mesh vertices and Pixel-wise Motion Consistency on rendered RGB-D observations. We introduce Articulate-100, a new benchmark of 100 articulated objects spanning 16 PartNet-Mobility categories. On this benchmark, ArtMesh outperforms prior 3DGS-based pipelines in joint parameter estimation and part-level geometric reconstruction, with the largest gains on objects with many movable parts. △ Less

Submitted 15 May, 2026; originally announced May 2026.

8DNA: 8D Neural Asset Light Transport by Distribution Learning

Authors: Liwen Wu, Haolin Lu, Bing Xu, Miloš Hašan, Ravi Ramamoorthi

Abstract: High-fidelity 3D assets exhibit intriguing global illumination effects like subsurface scattering, glossy interreflections, and fine-scale fiber scatterings, which often involve long scattering paths that are expensive to simulate. We introduce 8D neural assets (8DNA) to pre-bake these light transport effects into neural representations. Unlike prior methods that assume far-field lighting and prec… ▽ More High-fidelity 3D assets exhibit intriguing global illumination effects like subsurface scattering, glossy interreflections, and fine-scale fiber scatterings, which often involve long scattering paths that are expensive to simulate. We introduce 8D neural assets (8DNA) to pre-bake these light transport effects into neural representations. Unlike prior methods that assume far-field lighting and precompute light transport into 6D functions, 8DNA learns the full 8D light transport, enabling accurate rendering under near-field illumination. Our training leverages a distribution-learning formulation that learns light transport from forward path-traced samples, which produces less optimization variance with lower training budget than the prior regression-based approaches. Experiments show our 8DNA rendering closely matches path-traced results under various scene configurations, yet it achieves improved variance reduction and fast inference speeds on challenging assets. △ Less

Submitted 27 April, 2026; originally announced April 2026.

PhysConvex: Physics-Informed 3D Dynamic Convex Radiance Fields for Reconstruction and Simulation

Authors: Dan Wang, Xinrui Cui, Serge Belongie, Ravi Ramamoorthi

Abstract: Reconstructing and simulating dynamic 3D scenes with both visual realism and physical consistency remains a fundamental challenge. Existing neural representations, such as NeRFs and 3DGS, excel in appearance reconstruction but struggle to capture complex material deformation and dynamics. We propose PhysConvex, a Physics-informed 3D Dynamic Convex Radiance Field that unifies visual rendering and p… ▽ More Reconstructing and simulating dynamic 3D scenes with both visual realism and physical consistency remains a fundamental challenge. Existing neural representations, such as NeRFs and 3DGS, excel in appearance reconstruction but struggle to capture complex material deformation and dynamics. We propose PhysConvex, a Physics-informed 3D Dynamic Convex Radiance Field that unifies visual rendering and physical simulation. PhysConvex represents deformable radiance fields using physically grounded convex primitives governed by continuum mechanics. We introduce a boundary-driven dynamic convex representation that models deformation through vertex and surface dynamics, capturing spatially adaptive, non-uniform deformation, and evolving boundaries. To efficiently simulate complex geometries and heterogeneous materials, we further develop a reduced-order convex simulation that advects dynamic convex fields using neural skinning eigenmodes as shape- and material-aware deformation bases with time-varying reduced DOFs under Newtonian dynamics. Convex dynamics also offers compact, gap-free volumetric coverage, enhancing both geometric efficiency and simulation fidelity. Experiments demonstrate that PhysConvex achieves high-fidelity reconstruction of geometry, appearance, and physical properties from videos, outperforming existing methods. △ Less

Submitted 21 February, 2026; originally announced February 2026.

Instant Expressive Gaussian Head Avatars at Over 100 FPS

Authors: Kaiwen Jiang, Xueting Li, Seonwook Park, Ravi Ramamoorthi, Shalini De Mello, Koki Nagano

Abstract: Portrait animation has witnessed tremendous quality improvements thanks to recent advances in video diffusion models. However, these 2D methods often compromise 3D consistency and speed, limiting their applicability in real-world scenarios, such as digital twins or telepresence. In contrast, 3D-aware feedforward facial animation methods -- built upon 3D representations, such as neural radiance fie… ▽ More Portrait animation has witnessed tremendous quality improvements thanks to recent advances in video diffusion models. However, these 2D methods often compromise 3D consistency and speed, limiting their applicability in real-world scenarios, such as digital twins or telepresence. In contrast, 3D-aware feedforward facial animation methods -- built upon 3D representations, such as neural radiance fields or Gaussian splatting -- ensure 3D consistency and achieve faster inference speed, but come with inferior expression details. In this paper, we address this portrait animation trilemma (speed, 3D consistency, and expressiveness) and propose a pipeline that instantly converts an in-the-wild single image into a 3D-consistent, fast yet expressive animatable representation via a feed-forward encoder. Unlike previous computationally intensive global fusion mechanisms (e.g., multiple attention layers) for fusing 3D structural and animation information, our design employs an efficient lightweight local fusion strategy to achieve high animation expressivity. Furthermore, our animation representation is decoupled from the face's 3D representation and learns motion implicitly from data, eliminating the dependency on pre-defined parametric models that often constrain animation capabilities. Our method runs at 107.31 FPS for animation and pose control, representing a 3-4 order of magnitude speedup versus the state of the art while achieving comparable animation quality, thus surpassing alternative designs that trade speed for quality or vice versa. △ Less

Submitted 26 June, 2026; v1 submitted 18 December, 2025; originally announced December 2025.

Comments: Project website is https://research.nvidia.com/labs/amri/projects/instant4d

A Generalizable Light Transport 3D Embedding for Global Illumination

Authors: Bing Xu, Mukund Varma T, Cheng Wang, Tzu-Mao Li, Lifan Wu, Bartlomiej Wronski, Ravi Ramamoorthi, Marco Salvi

Abstract: Global illumination (GI) is essential for realistic rendering but remains computationally expensive due to the complexity of simulating indirect light transport. Recent neural methods have mainly relied on per-scene optimization, sometimes extended to handle changes in camera or geometry. Efforts toward cross-scene generalization have largely stayed in 2D screen space, such as neural denoising or… ▽ More Global illumination (GI) is essential for realistic rendering but remains computationally expensive due to the complexity of simulating indirect light transport. Recent neural methods have mainly relied on per-scene optimization, sometimes extended to handle changes in camera or geometry. Efforts toward cross-scene generalization have largely stayed in 2D screen space, such as neural denoising or G-buffer based GI prediction, which often suffer from view inconsistency and limited spatial understanding. We propose a generalizable 3D light transport embedding that approximates global illumination directly from 3D scene configurations, without using rasterized or path-traced cues. Each scene is represented as a point cloud with geometric and material features. A scalable transformer models global point-to-point interactions to encode these features into neural primitives. At render time, each query point retrieves nearby primitives via nearest-neighbor search and aggregates their latent features through cross-attention to predict the desired rendering quantity. We demonstrate results on diffuse global illumination prediction across diverse indoor scenes with varying layouts, geometry, and materials. The embedding trained for irradiance estimation can be quickly adapted to new rendering tasks with limited fine-tuning. We also present preliminary results for spatial-directional radiance field estimation for glossy materials and show how the normalized field can accelerate unbiased path guiding. This approach highlights a path toward integrating learned priors into rendering pipelines without explicit ray-traced illumination cues. △ Less

Submitted 12 June, 2026; v1 submitted 20 October, 2025; originally announced October 2025.

Comments: SIGGRAPH 2026

Spectral Prefiltering of Neural Fields

Authors: Mustafa B. Yaldiz, Ishit Mehta, Nithin Raghavan, Andreas Meuleman, Tzu-Mao Li, Ravi Ramamoorthi

Abstract: Neural fields excel at representing continuous visual signals but typically operate at a single, fixed resolution. We present a simple yet powerful method to optimize neural fields that can be prefiltered in a single forward pass. Key innovations and features include: (1) We perform convolutional filtering in the input domain by analytically scaling Fourier feature embeddings with the filter's fre… ▽ More Neural fields excel at representing continuous visual signals but typically operate at a single, fixed resolution. We present a simple yet powerful method to optimize neural fields that can be prefiltered in a single forward pass. Key innovations and features include: (1) We perform convolutional filtering in the input domain by analytically scaling Fourier feature embeddings with the filter's frequency response. (2) This closed-form modulation generalizes beyond Gaussian filtering and supports other parametric filters (Box and Lanczos) that are unseen at training time. (3) We train the neural field using single-sample Monte Carlo estimates of the filtered signal. Our method is fast during both training and inference, and imposes no additional constraints on the network architecture. We show quantitative and qualitative improvements over existing methods for neural-field filtering. △ Less

Submitted 4 February, 2026; v1 submitted 9 October, 2025; originally announced October 2025.

Comments: 16 pages, 10 figures, Website: https://myaldiz.info/assets/spnf

Journal ref: Proceedings of the SIGGRAPH Asia 2025 Conference Papers, Article No. 87, pp. 1-12, 2025

Differentiable Light Transport with Gaussian Surfels via Adapted Radiosity for Efficient Relighting and Geometry Reconstruction

Authors: Kaiwen Jiang, Jia-Mu Sun, Zilu Li, Dan Wang, Tzu-Mao Li, Ravi Ramamoorthi

Abstract: Radiance fields have gained tremendous success with applications ranging from novel view synthesis to geometry reconstruction, especially with the advent of Gaussian splatting. However, they sacrifice modeling of material reflective properties and lighting conditions, leading to significant geometric ambiguities and the inability to easily perform relighting. One way to address these limitations i… ▽ More Radiance fields have gained tremendous success with applications ranging from novel view synthesis to geometry reconstruction, especially with the advent of Gaussian splatting. However, they sacrifice modeling of material reflective properties and lighting conditions, leading to significant geometric ambiguities and the inability to easily perform relighting. One way to address these limitations is to incorporate physically-based rendering, but it has been prohibitively expensive to include full global illumination within the inner loop of the optimization. Therefore, previous works adopt simplifications that make the whole optimization with global illumination effects efficient but less accurate. In this work, we adopt Gaussian surfels as the primitives and build an efficient framework for differentiable light transport, inspired from the classic radiosity theory. The whole framework operates in the coefficient space of spherical harmonics, enabling both diffuse and specular materials. We extend the classic radiosity into non-binary visibility and semi-opaque primitives, propose novel solvers to efficiently solve the light transport, and derive the backward pass for gradient optimizations, which is more efficient than auto-differentiation. During inference, we achieve view-independent rendering where light transport need not be recomputed under viewpoint changes, enabling hundreds of FPS for global illumination effects, including view-dependent reflections using a spherical harmonics representation. Through extensive qualitative and quantitative experiments, we demonstrate superior geometry reconstruction, view synthesis and relighting than previous inverse rendering baselines, or data-driven baselines given relatively sparse datasets with known or unknown lighting conditions. △ Less

Submitted 29 September, 2025; v1 submitted 22 September, 2025; originally announced September 2025.

MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild

Authors: Deming Li, Kaiwen Jiang, Yutao Tang, Ravi Ramamoorthi, Rama Chellappa, Cheng Peng

Abstract: In-the-wild photo collections often contain limited volumes of imagery and exhibit multiple appearances, e.g., taken at different times of day or seasons, posing significant challenges to scene reconstruction and novel view synthesis. Although recent adaptations of Neural Radiance Field (NeRF) and 3D Gaussian Splatting (3DGS) have improved in these areas, they tend to oversmooth and are prone to o… ▽ More In-the-wild photo collections often contain limited volumes of imagery and exhibit multiple appearances, e.g., taken at different times of day or seasons, posing significant challenges to scene reconstruction and novel view synthesis. Although recent adaptations of Neural Radiance Field (NeRF) and 3D Gaussian Splatting (3DGS) have improved in these areas, they tend to oversmooth and are prone to overfitting. In this paper, we present MS-GS, a novel framework designed with Multi-appearance capabilities in Sparse-view scenarios using 3DGS. To address the lack of support due to sparse initializations, our approach is built on the geometric priors elicited from monocular depth estimations. The key lies in extracting and utilizing local semantic regions with a Structure-from-Motion (SfM) points anchored algorithm for reliable alignment and geometry cues. Then, to introduce multi-view constraints, we propose a series of geometry-guided supervision steps at virtual views in pixel and feature levels to encourage 3D consistency and reduce overfitting. We also introduce a dataset and an in-the-wild experiment setting to set up more realistic benchmarks. We demonstrate that MS-GS achieves photorealistic renderings under various challenging sparse-view and multi-appearance conditions, and outperforms existing approaches significantly across different datasets. △ Less

Submitted 23 October, 2025; v1 submitted 18 September, 2025; originally announced September 2025.

Neural BRDF Importance Sampling by Reparameterization

Authors: Liwen Wu, Sai Bi, Zexiang Xu, Hao Tan, Kai Zhang, Fujun Luan, Haolin Lu, Ravi Ramamoorthi

Abstract: Neural bidirectional reflectance distribution functions (BRDFs) have emerged as popular material representations for enhancing realism in physically-based rendering. Yet their importance sampling remains a significant challenge. In this paper, we introduce a reparameterization-based formulation of neural BRDF importance sampling that seamlessly integrates into the standard rendering pipeline with… ▽ More Neural bidirectional reflectance distribution functions (BRDFs) have emerged as popular material representations for enhancing realism in physically-based rendering. Yet their importance sampling remains a significant challenge. In this paper, we introduce a reparameterization-based formulation of neural BRDF importance sampling that seamlessly integrates into the standard rendering pipeline with precise generation of BRDF samples. The reparameterization-based formulation transfers the distribution learning task to a problem of identifying BRDF integral substitutions. In contrast to previous methods that rely on invertible networks and multi-step inference to reconstruct BRDF distributions, our model removes these constraints, which offers greater flexibility and efficiency. Our variance and performance analysis demonstrates that our reparameterization method achieves the best variance reduction in neural BRDF renderings while maintaining high inference speeds compared to existing baselines. △ Less

Submitted 13 May, 2025; originally announced May 2025.

Position-Normal Manifold for Efficient Glint Rendering on High-Resolution Normal Maps

Authors: Liwen Wu, Fujun Luan, Miloš Hašan, Ravi Ramamoorthi

Abstract: Detailed microstructures on specular objects often exhibit intriguing glinty patterns under high-frequency lighting, which is challenging to render using a conventional normal-mapped BRDF. In this paper, we present a manifold-based formulation of the glint normal distribution functions (NDF) that precisely captures the surface normal distributions over queried footprints. The manifold-based formul… ▽ More Detailed microstructures on specular objects often exhibit intriguing glinty patterns under high-frequency lighting, which is challenging to render using a conventional normal-mapped BRDF. In this paper, we present a manifold-based formulation of the glint normal distribution functions (NDF) that precisely captures the surface normal distributions over queried footprints. The manifold-based formulation transfers the integration for the glint NDF construction to a problem of mesh intersections. Compared to previous works that rely on complex numerical approximations, our integral solution is exact and much simpler to compute, which also allows an easy adaptation of a mesh clustering hierarchy to accelerate the NDF evaluation of large footprints. Our performance and quality analysis shows that our NDF formulation achieves similar glinty appearance compared to the baselines but is an order of magnitude faster. Within this framework, we further present a novel derivation of analytical shadow-masking for normal-mapped diffuse surfaces -- a component that is often ignored in previous works. △ Less

Submitted 13 May, 2025; originally announced May 2025.

TranSplat: Instant Object Relighting in Gaussian Splatting via Spherical Harmonic Radiance Transfer

Authors: Boyang Tony Yu, Yanlin Jin, Yun He, Akshat Dave, Ravi Ramamoorthi, Guha Balakrishnan

Abstract: We present TranSplat, a method for instant, accurate object relighting within the Gaussian Splatting (GS) framework. Rather than relying on costly inverse rendering routines, we propose a BRDF-free radiance transfer strategy that analytically modulates the spherical harmonic (SH) appearance coefficients of an object's 2D Gaussian surfels using per-normal irradiance ratios derived from source and t… ▽ More We present TranSplat, a method for instant, accurate object relighting within the Gaussian Splatting (GS) framework. Rather than relying on costly inverse rendering routines, we propose a BRDF-free radiance transfer strategy that analytically modulates the spherical harmonic (SH) appearance coefficients of an object's 2D Gaussian surfels using per-normal irradiance ratios derived from source and target environment maps. To handle view-dependent and glossy appearances without explicit material estimation, we introduce a specularity-aware dual-path SH transfer strategy that adapts higher-order SH bands in the reflection domain. Additionally, we propose a lightweight SH-domain self-shadowing module to ensure physically realistic occlusion without explicit mesh raycasting. Operating as a post-processing step, TranSplat requires no additional GS retraining for a pair of source and target scenes. Evaluations on synthetic and real-world objects demonstrate state-of-the-art accuracy, outperforming recent inverse-rendering and diffusion-based GS relighting methods across most conditions, all while completing relighting operations in under one second. Although bounded by radially symmetric BRDF approximations and the low-pass nature of the SH basis, TranSplat produces perceptually realistic renderings even for glossy, complex materials, establishing a valuable, lightweight path forward for GS relighting. △ Less

Submitted 21 July, 2026; v1 submitted 28 March, 2025; originally announced March 2025.

Comments: ICCP 2026

Locally Orderless Images for Optimization in Differentiable Rendering

Authors: Ishit Mehta, Manmohan Chandraker, Ravi Ramamoorthi

Abstract: Problems in differentiable rendering often involve optimizing scene parameters that cause motion in image space. The gradients for such parameters tend to be sparse, leading to poor convergence. While existing methods address this sparsity through proxy gradients such as topological derivatives or lagrangian derivatives, they make simplifying assumptions about rendering. Multi-resolution image pyr… ▽ More Problems in differentiable rendering often involve optimizing scene parameters that cause motion in image space. The gradients for such parameters tend to be sparse, leading to poor convergence. While existing methods address this sparsity through proxy gradients such as topological derivatives or lagrangian derivatives, they make simplifying assumptions about rendering. Multi-resolution image pyramids offer an alternative approach but prove unreliable in practice. We introduce a method that uses locally orderless images, where each pixel maps to a histogram of intensities that preserves local variations in appearance. Using an inverse rendering objective that minimizes histogram distance, our method extends support for sparsely defined image gradients and recovers optimal parameters. We validate our method on various inverse problems using both synthetic and real data. △ Less

Submitted 27 March, 2025; originally announced March 2025.

Comments: CVPR 2025. Project: https://ishit.github.io/loir/

A Differentiable Wave Optics Model for End-to-End Computational Imaging System Optimization

Authors: Chi-Jui Ho, Yash Belhe, Steve Rotenberg, Ravi Ramamoorthi, Tzu-Mao Li, Nicholas Antipa

Abstract: End-to-end optimization, which simultaneously optimizes optics and algorithms, has emerged as a powerful data-driven method for computational imaging system design. This method achieves joint optimization through backpropagation by incorporating differentiable optics simulators to generate measurements and algorithms to extract information from measurements. However, due to high computational cost… ▽ More End-to-end optimization, which simultaneously optimizes optics and algorithms, has emerged as a powerful data-driven method for computational imaging system design. This method achieves joint optimization through backpropagation by incorporating differentiable optics simulators to generate measurements and algorithms to extract information from measurements. However, due to high computational costs, it is challenging to model both aberration and diffraction in light transport for end-to-end optimization of compound optics. Therefore, most existing methods compromise physical accuracy by neglecting wave optics effects or off-axis aberrations, which raises concerns about the robustness of the resulting designs. In this paper, we propose a differentiable optics simulator that efficiently models both aberration and diffraction for compound optics. Using the simulator, we conduct end-to-end optimization on scene reconstruction and classification. Experimental results demonstrate that both lenses and algorithms adopt different configurations depending on whether wave optics is modeled. We also show that systems optimized without wave optics suffer from performance degradation when wave optics effects are introduced during testing. These findings underscore the importance of accurate wave optics modeling in optimizing imaging systems for robust, high-performance applications. △ Less

Submitted 6 August, 2025; v1 submitted 12 December, 2024; originally announced December 2024.

SimVS: Simulating World Inconsistencies for Robust View Synthesis

Authors: Alex Trevithick, Roni Paiss, Philipp Henzler, Dor Verbin, Rundi Wu, Hadi Alzayer, Ruiqi Gao, Ben Poole, Jonathan T. Barron, Aleksander Holynski, Ravi Ramamoorthi, Pratul P. Srinivasan

Abstract: Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are difficult to model explicitly. We present an approach for leveraging generative video models to simulate the inconsistencies in the world that can occur during cap… ▽ More Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are difficult to model explicitly. We present an approach for leveraging generative video models to simulate the inconsistencies in the world that can occur during capture. We use this process, along with existing multi-view datasets, to create synthetic data for training a multi-view harmonization network that is able to reconcile inconsistent observations into a consistent 3D scene. We demonstrate that our world-simulation strategy significantly outperforms traditional augmentation methods in handling real-world scene variations, thereby enabling highly accurate static 3D reconstructions in the presence of a variety of challenging inconsistencies. Project page: https://alextrevithick.github.io/simvs △ Less

Submitted 10 December, 2024; originally announced December 2024.

Comments: Project page: https://alextrevithick.github.io/simvs

Volumetrically Consistent 3D Gaussian Rasterization

Authors: Chinmay Talegaonkar, Yash Belhe, Ravi Ramamoorthi, Nicholas Antipa

Abstract: Recently, 3D Gaussian Splatting (3DGS) has enabled photorealistic view synthesis at high inference speeds. However, its splatting-based rendering model makes several approximations to the rendering equation, reducing physical accuracy. We show that the core approximations in splatting are unnecessary, even within a rasterizer; We instead volumetrically integrate 3D Gaussians directly to compute th… ▽ More Recently, 3D Gaussian Splatting (3DGS) has enabled photorealistic view synthesis at high inference speeds. However, its splatting-based rendering model makes several approximations to the rendering equation, reducing physical accuracy. We show that the core approximations in splatting are unnecessary, even within a rasterizer; We instead volumetrically integrate 3D Gaussians directly to compute the transmittance across them analytically. We use this analytic transmittance to derive more physically-accurate alpha values than 3DGS, which can directly be used within their framework. The result is a method that more closely follows the volume rendering equation (similar to ray-tracing) while enjoying the speed benefits of rasterization. Our method represents opaque surfaces with higher accuracy and fewer points than 3DGS. This enables it to outperform 3DGS for view synthesis (measured in SSIM and LPIPS). Being volumetrically consistent also enables our method to work out of the box for tomography. We match the state-of-the-art 3DGS-based tomography method with fewer points. Our code is publicly available at: https://github.com/chinmay0301ucsd/Vol3DGS △ Less

Submitted 20 May, 2025; v1 submitted 4 December, 2024; originally announced December 2024.

Geometry Field Splatting with Gaussian Surfels

Authors: Kaiwen Jiang, Venkataram Sivaram, Cheng Peng, Ravi Ramamoorthi

Abstract: Geometric reconstruction of opaque surfaces from images is a longstanding challenge in computer vision, with renewed interest from volumetric view synthesis algorithms using radiance fields. We leverage the geometry field proposed in recent work for stochastic opaque surfaces, which can then be converted to volume densities. We adapt Gaussian kernels or surfels to splat the geometry field rather t… ▽ More Geometric reconstruction of opaque surfaces from images is a longstanding challenge in computer vision, with renewed interest from volumetric view synthesis algorithms using radiance fields. We leverage the geometry field proposed in recent work for stochastic opaque surfaces, which can then be converted to volume densities. We adapt Gaussian kernels or surfels to splat the geometry field rather than the volume, enabling precise reconstruction of opaque solids. Our first contribution is to derive an efficient and almost exact differentiable rendering algorithm for geometry fields parameterized by Gaussian surfels, while removing current approximations involving Taylor series and no self-attenuation. Next, we address the discontinuous loss landscape when surfels cluster near geometry, showing how to guarantee that the rendered color is a continuous function of the colors of the kernels, irrespective of ordering. Finally, we use latent representations with spherical harmonics encoded reflection vectors rather than spherical harmonics encoded colors to better address specular surfaces. We demonstrate significant improvement in the quality of reconstructed 3D surfaces on widely-used datasets. △ Less

Submitted 27 March, 2025; v1 submitted 25 November, 2024; originally announced November 2024.

Efficient Scene Appearance Aggregation for Level-of-Detail Rendering

Authors: Yang Zhou, Tao Huang, Ravi Ramamoorthi, Pradeep Sen, Ling-Qi Yan

Abstract: Creating an appearance-preserving level-of-detail (LoD) representation for arbitrary 3D scenes is a challenging problem. The appearance of a scene is an intricate combination of both geometry and material models, and is further complicated by correlation due to the spatial configuration of scene elements. We present a novel volumetric representation for the aggregated appearance of complex scenes… ▽ More Creating an appearance-preserving level-of-detail (LoD) representation for arbitrary 3D scenes is a challenging problem. The appearance of a scene is an intricate combination of both geometry and material models, and is further complicated by correlation due to the spatial configuration of scene elements. We present a novel volumetric representation for the aggregated appearance of complex scenes and an efficient pipeline for LoD generation and rendering. The core of our representation is the Aggregated Bidirectional Scattering Distribution Function (ABSDF) that summarizes the far-field appearance of all surfaces inside a voxel. We propose a closed-form factorization of the ABSDF that accounts for spatially varying and orientation-varying material parameters. We tackle the challenge of capturing the correlation existing locally within a voxel and globally across different parts of the scene. Our method faithfully reproduces appearance and achieves higher quality than existing scene filtering methods while being inherently efficient to render. The memory footprint and rendering cost of our representation are independent of the original scene complexity. △ Less

Submitted 18 August, 2024; originally announced September 2024.

Journal ref: ACM Trans. Graph. 44, 1, Article 8 (February 2025), 23 pages

Sampling for View Synthesis: From Local Light Field Fusion to Neural Radiance Fields and Beyond

Authors: Ravi Ramamoorthi

Abstract: Capturing and rendering novel views of complex real-world scenes is a long-standing problem in computer graphics and vision, with applications in augmented and virtual reality, immersive experiences and 3D photography. The advent of deep learning has enabled revolutionary advances in this area, classically known as image-based rendering. However, previous approaches require intractably dense view… ▽ More Capturing and rendering novel views of complex real-world scenes is a long-standing problem in computer graphics and vision, with applications in augmented and virtual reality, immersive experiences and 3D photography. The advent of deep learning has enabled revolutionary advances in this area, classically known as image-based rendering. However, previous approaches require intractably dense view sampling or provide little or no guidance for how users should sample views of a scene to reliably render high-quality novel views. Local light field fusion proposes an algorithm for practical view synthesis from an irregular grid of sampled views that first expands each sampled view into a local light field via a multiplane image scene representation, then renders novel views by blending adjacent local light fields. Crucially, we extend traditional plenoptic sampling theory to derive a bound that specifies precisely how densely users should sample views of a given scene when using our algorithm. We achieve the perceptual quality of Nyquist rate view sampling while using up to 4000x fewer views. Subsequent developments have led to new scene representations for deep learning with view synthesis, notably neural radiance fields, but the problem of sparse view synthesis from a small number of images has only grown in importance. We reprise some of the recent results on sparse and even single image view synthesis, while posing the question of whether prescriptive sampling guidelines are feasible for the new generation of image-based rendering algorithms. △ Less

Submitted 8 August, 2024; originally announced August 2024.

Comments: Article written for Frontiers of Science Award, International Congress on Basic Science, 2024

Residual path integrals for re-rendering

Authors: Bing Xu, Tzu-Mao Li, Iliyan Georgiev, Trevor Hedstrom, Ravi Ramamoorthi

Abstract: Conventional rendering techniques are primarily designed and optimized for single-frame rendering. In practical applications, such as scene editing and animation rendering, users frequently encounter scenes where only a small portion is modified between consecutive frames. In this paper, we develop a novel approach to incremental re-rendering of scenes with dynamic objects, where only a small part… ▽ More Conventional rendering techniques are primarily designed and optimized for single-frame rendering. In practical applications, such as scene editing and animation rendering, users frequently encounter scenes where only a small portion is modified between consecutive frames. In this paper, we develop a novel approach to incremental re-rendering of scenes with dynamic objects, where only a small part of a scene moves from one frame to the next. We formulate the difference (or residual) in the image between two frames as a (correlated) light-transport integral which we call the residual path integral. Efficient numerical solution of this integral then involves (1)~devising importance sampling strategies to focus on paths with non-zero residual-transport contributions and (2)~choosing appropriate mappings between the native path spaces of the two frames. We introduce a set of path importance sampling strategies that trace from the moving object(s) which are the sources of residual energy. We explore path mapping strategies that generalize those from gradient-domain path tracing to our importance sampling techniques specially for dynamic scenes. Additionally, our formulation can be applied to material editing as a simpler special case. We demonstrate speed-ups over previous correlated sampling of path differences and over rendering the new frame independently. Our formulation brings new insights into the re-rendering problem and paves the way for devising new types of sampling techniques and path mappings with different trade-offs. △ Less

Submitted 23 June, 2024; originally announced June 2024.

Comments: 14 pages, 13 figures

ACM Class: I.3.0

Fluid Implicit Particles on Coadjoint Orbits

Authors: Mohammad Sina Nabizadeh, Ritoban Roy-Chowdhury, Hang Yin, Ravi Ramamoorthi, Albert Chern

Abstract: We propose Coadjoint Orbit FLIP (CO-FLIP), a high order accurate, structure preserving fluid simulation method in the hybrid Eulerian-Lagrangian framework. We start with a Hamiltonian formulation of the incompressible Euler Equations, and then, using a local, explicit, and high order divergence free interpolation, construct a modified Hamiltonian system that governs our discrete Euler flow. The re… ▽ More We propose Coadjoint Orbit FLIP (CO-FLIP), a high order accurate, structure preserving fluid simulation method in the hybrid Eulerian-Lagrangian framework. We start with a Hamiltonian formulation of the incompressible Euler Equations, and then, using a local, explicit, and high order divergence free interpolation, construct a modified Hamiltonian system that governs our discrete Euler flow. The resulting discretization, when paired with a geometric time integration scheme, is energy and circulation preserving (formally the flow evolves on a coadjoint orbit) and is similar to the Fluid Implicit Particle (FLIP) method. CO-FLIP enjoys multiple additional properties including that the pressure projection is exact in the weak sense, and the particle-to-grid transfer is an exact inverse of the grid-to-particle interpolation. The method is demonstrated numerically with outstanding stability, energy, and Casimir preservation. We show that the method produces benchmarks and turbulent visual effects even at low grid resolutions. △ Less

Submitted 19 September, 2024; v1 submitted 3 June, 2024; originally announced June 2024.

Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling

Authors: Liwen Wu, Sai Bi, Zexiang Xu, Fujun Luan, Kai Zhang, Iliyan Georgiev, Kalyan Sunkavalli, Ravi Ramamoorthi

Abstract: Novel-view synthesis of specular objects like shiny metals or glossy paints remains a significant challenge. Not only the glossy appearance but also global illumination effects, including reflections of other objects in the environment, are critical components to faithfully reproduce a scene. In this paper, we present Neural Directional Encoding (NDE), a view-dependent appearance encoding of neura… ▽ More Novel-view synthesis of specular objects like shiny metals or glossy paints remains a significant challenge. Not only the glossy appearance but also global illumination effects, including reflections of other objects in the environment, are critical components to faithfully reproduce a scene. In this paper, we present Neural Directional Encoding (NDE), a view-dependent appearance encoding of neural radiance fields (NeRF) for rendering specular objects. NDE transfers the concept of feature-grid-based spatial encoding to the angular domain, significantly improving the ability to model high-frequency angular signals. In contrast to previous methods that use encoding functions with only angular input, we additionally cone-trace spatial features to obtain a spatially varying directional encoding, which addresses the challenging interreflection effects. Extensive experiments on both synthetic and real datasets show that a NeRF model with NDE (1) outperforms the state of the art on view synthesis of specular objects, and (2) works with small networks to allow fast (real-time) inference. The project webpage and source code are available at: \url{https://lwwu2.github.io/nde/}. △ Less

Submitted 23 May, 2024; originally announced May 2024.

Comments: Accepted to CVPR 2024

A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose

Authors: Kaiwen Jiang, Yang Fu, Mukund Varma T, Yash Belhe, Xiaolong Wang, Hao Su, Ravi Ramamoorthi

Abstract: Novel view synthesis from a sparse set of input images is a challenging problem of great practical interest, especially when camera poses are absent or inaccurate. Direct optimization of camera poses and usage of estimated depths in neural radiance field algorithms usually do not produce good results because of the coupling between poses and depths, and inaccuracies in monocular depth estimation.… ▽ More Novel view synthesis from a sparse set of input images is a challenging problem of great practical interest, especially when camera poses are absent or inaccurate. Direct optimization of camera poses and usage of estimated depths in neural radiance field algorithms usually do not produce good results because of the coupling between poses and depths, and inaccuracies in monocular depth estimation. In this paper, we leverage the recent 3D Gaussian splatting method to develop a novel construct-and-optimize method for sparse view synthesis without camera poses. Specifically, we construct a solution progressively by using monocular depth and projecting pixels back into the 3D world. During construction, we optimize the solution by detecting 2D correspondences between training views and the corresponding rendered images. We develop a unified differentiable pipeline for camera registration and adjustment of both camera poses and depths, followed by back-projection. We also introduce a novel notion of an expected surface in Gaussian splatting, which is critical to our optimization. These steps enable a coarse solution, which can then be low-pass filtered and refined using standard optimization methods. We demonstrate results on the Tanks and Temples and Static Hikes datasets with as few as three widely-spaced views, showing significantly better quality than competing methods, including those with approximate camera pose information. Moreover, our results improve with more views and outperform previous InstantNGP and Gaussian Splatting algorithms even when using half the dataset. Project page: https://raymondjiangkw.github.io/cogs.github.io/ △ Less

Submitted 10 June, 2024; v1 submitted 6 May, 2024; originally announced May 2024.

RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion

Authors: Jaidev Shriram, Alex Trevithick, Lingjie Liu, Ravi Ramamoorthi

Abstract: We introduce RealmDreamer, a technique for generating forward-facing 3D scenes from text descriptions. Our method optimizes a 3D Gaussian Splatting representation to match complex text prompts using pretrained diffusion models. Our key insight is to leverage 2D inpainting diffusion models conditioned on an initial scene estimate to provide low variance supervision for unknown regions during 3D dis… ▽ More We introduce RealmDreamer, a technique for generating forward-facing 3D scenes from text descriptions. Our method optimizes a 3D Gaussian Splatting representation to match complex text prompts using pretrained diffusion models. Our key insight is to leverage 2D inpainting diffusion models conditioned on an initial scene estimate to provide low variance supervision for unknown regions during 3D distillation. In conjunction, we imbue high-fidelity geometry with geometric distillation from a depth diffusion model, conditioned on samples from the inpainting model. We find that the initialization of the optimization is crucial, and provide a principled methodology for doing so. Notably, our technique doesn't require video or multi-view data and can synthesize various high-quality 3D scenes in different styles with complex layouts. Further, the generality of our method allows 3D synthesis from a single image. As measured by a comprehensive user study, our method outperforms all existing approaches, preferred by 88-95%. Project Page: https://realmdreamer.github.io/ △ Less

Submitted 11 March, 2025; v1 submitted 10 April, 2024; originally announced April 2024.

Comments: Published at 3DV 2025

Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D

Authors: Mukund Varma T, Peihao Wang, Zhiwen Fan, Zhangyang Wang, Hao Su, Ravi Ramamoorthi

Abstract: In recent years, there has been an explosion of 2D vision models for numerous tasks such as semantic segmentation, style transfer or scene editing, enabled by large-scale 2D image datasets. At the same time, there has been renewed interest in 3D scene representations such as neural radiance fields from multi-view images. However, the availability of 3D or multiview data is still substantially limi… ▽ More In recent years, there has been an explosion of 2D vision models for numerous tasks such as semantic segmentation, style transfer or scene editing, enabled by large-scale 2D image datasets. At the same time, there has been renewed interest in 3D scene representations such as neural radiance fields from multi-view images. However, the availability of 3D or multiview data is still substantially limited compared to 2D image datasets, making extending 2D vision models to 3D data highly desirable but also very challenging. Indeed, extending a single 2D vision operator like scene editing to 3D typically requires a highly creative method specialized to that task and often requires per-scene optimization. In this paper, we ask the question of whether any 2D vision model can be lifted to make 3D consistent predictions. We answer this question in the affirmative; our new Lift3D method trains to predict unseen views on feature spaces generated by a few visual models (i.e. DINO and CLIP), but then generalizes to novel vision operators and tasks, such as style transfer, super-resolution, open vocabulary segmentation and image colorization; for some of these tasks, there is no comparable previous 3D method. In many cases, we even outperform state-of-the-art methods specialized for the task in question. Moreover, Lift3D is a zero-shot method, in the sense that it requires no task-specific training, nor scene-specific optimization. △ Less

Submitted 27 March, 2024; originally announced March 2024.

Comments: Computer Vision and Pattern Recognition Conference (CVPR), 2024

What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs

Authors: Alex Trevithick, Matthew Chan, Towaki Takikawa, Umar Iqbal, Shalini De Mello, Manmohan Chandraker, Ravi Ramamoorthi, Koki Nagano

Abstract: 3D-aware Generative Adversarial Networks (GANs) have shown remarkable progress in learning to generate multi-view-consistent images and 3D geometries of scenes from collections of 2D images via neural volume rendering. Yet, the significant memory and computational costs of dense sampling in volume rendering have forced 3D GANs to adopt patch-based training or employ low-resolution rendering with p… ▽ More 3D-aware Generative Adversarial Networks (GANs) have shown remarkable progress in learning to generate multi-view-consistent images and 3D geometries of scenes from collections of 2D images via neural volume rendering. Yet, the significant memory and computational costs of dense sampling in volume rendering have forced 3D GANs to adopt patch-based training or employ low-resolution rendering with post-processing 2D super resolution, which sacrifices multiview consistency and the quality of resolved geometry. Consequently, 3D GANs have not yet been able to fully resolve the rich 3D geometry present in 2D images. In this work, we propose techniques to scale neural volume rendering to the much higher resolution of native 2D images, thereby resolving fine-grained 3D geometry with unprecedented detail. Our approach employs learning-based samplers for accelerating neural rendering for 3D GAN training using up to 5 times fewer depth samples. This enables us to explicitly "render every pixel" of the full-resolution image during training and inference without post-processing superresolution in 2D. Together with our strategy to learn high-quality surface geometry, our method synthesizes high-resolution 3D geometry and strictly view-consistent images while maintaining image quality on par with baselines relying on post-processing super resolution. We demonstrate state-of-the-art 3D gemetric quality on FFHQ and AFHQ, setting a new standard for unsupervised learning of 3D shapes in 3D GANs. △ Less

Submitted 4 January, 2024; originally announced January 2024.

Comments: See our project page: https://research.nvidia.com/labs/nxp/wysiwyg/

Neural BSSRDF: Object Appearance Representation Including Heterogeneous Subsurface Scattering

Authors: Thomson TG, Jeppe Revall Frisvad, Ravi Ramamoorthi, Henrik Wann Jensen

Abstract: Monte Carlo rendering of translucent objects with heterogeneous scattering properties is often expensive both in terms of memory and computation. If we do path tracing and use a high dynamic range lighting environment, the rendering becomes computationally heavy. We propose a compact and efficient neural method for representing and rendering the appearance of heterogeneous translucent objects. The… ▽ More Monte Carlo rendering of translucent objects with heterogeneous scattering properties is often expensive both in terms of memory and computation. If we do path tracing and use a high dynamic range lighting environment, the rendering becomes computationally heavy. We propose a compact and efficient neural method for representing and rendering the appearance of heterogeneous translucent objects. The neural representation function resembles a bidirectional scattering-surface reflectance distribution function (BSSRDF). However, conventional BSSRDF models assume a planar half-space medium and only surface variation of the material, which is often not a good representation of the appearance of real-world objects. Our method represents the BSSRDF of a full object taking its geometry and heterogeneities into account. This is similar to a neural radiance field, but our representation works for an arbitrary distant lighting environment. In a sense, we present a version of neural precomputed radiance transfer that captures all-frequency relighting of heterogeneous translucent objects. We use a multi-layer perceptron (MLP) with skip connections to represent the appearance of an object as a function of spatial position, direction of observation, and direction of incidence. The latter is considered a directional light incident across the entire non-self-shadowed part of the object. We demonstrate the ability of our method to store highly complex materials while having high accuracy when comparing to reference images of the represented object in unseen lighting environments. As compared with path tracing of a heterogeneous light scattering volume behind a refractive interface, our method more easily enables importance sampling of the directions of incidence and can be integrated into existing rendering frameworks while achieving interactive frame rates. △ Less

Submitted 25 December, 2023; originally announced December 2023.

OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects

Authors: Isabella Liu, Linghao Chen, Ziyang Fu, Liwen Wu, Haian Jin, Zhong Li, Chin Ming Ryan Wong, Yi Xu, Ravi Ramamoorthi, Zexiang Xu, Hao Su

Abstract: We introduce OpenIllumination, a real-world dataset containing over 108K images of 64 objects with diverse materials, captured under 72 camera views and a large number of different illuminations. For each image in the dataset, we provide accurate camera parameters, illumination ground truth, and foreground segmentation masks. Our dataset enables the quantitative evaluation of most inverse renderin… ▽ More We introduce OpenIllumination, a real-world dataset containing over 108K images of 64 objects with diverse materials, captured under 72 camera views and a large number of different illuminations. For each image in the dataset, we provide accurate camera parameters, illumination ground truth, and foreground segmentation masks. Our dataset enables the quantitative evaluation of most inverse rendering and material decomposition methods for real objects. We examine several state-of-the-art inverse rendering methods on our dataset and compare their performances. The dataset and code can be found on the project page: https://oppo-us-research.github.io/OpenIllumination. △ Less

Submitted 1 February, 2024; v1 submitted 14 September, 2023; originally announced September 2023.

A Theory of Topological Derivatives for Inverse Rendering of Geometry

Authors: Ishit Mehta, Manmohan Chandraker, Ravi Ramamoorthi

Abstract: We introduce a theoretical framework for differentiable surface evolution that allows discrete topology changes through the use of topological derivatives for variational optimization of image functionals. While prior methods for inverse rendering of geometry rely on silhouette gradients for topology changes, such signals are sparse. In contrast, our theory derives topological derivatives that rel… ▽ More We introduce a theoretical framework for differentiable surface evolution that allows discrete topology changes through the use of topological derivatives for variational optimization of image functionals. While prior methods for inverse rendering of geometry rely on silhouette gradients for topology changes, such signals are sparse. In contrast, our theory derives topological derivatives that relate the introduction of vanishing holes and phases to changes in image intensity. As a result, we enable differentiable shape perturbations in the form of hole or phase nucleation. We validate the proposed theory with optimization of closed curves in 2D and surfaces in 3D to lend insights into limitations of current methods and enable improved applications such as image vectorization, vector-graphics generation from text prompts, single-image reconstruction of shape ambigrams and multi-view 3D reconstruction. △ Less

Submitted 18 August, 2023; originally announced August 2023.

Comments: ICCV 23; Project Page at https://ishit.github.io/td/

NeRFs: The Search for the Best 3D Representation

Authors: Ravi Ramamoorthi

Abstract: Neural Radiance Fields or NeRFs have become the representation of choice for problems in view synthesis or image-based rendering, as well as in many other applications across computer graphics and vision, and beyond. At their core, NeRFs describe a new representation of 3D scenes or 3D geometry. Instead of meshes, disparity maps, multiplane images or even voxel grids, they represent the scene as a… ▽ More Neural Radiance Fields or NeRFs have become the representation of choice for problems in view synthesis or image-based rendering, as well as in many other applications across computer graphics and vision, and beyond. At their core, NeRFs describe a new representation of 3D scenes or 3D geometry. Instead of meshes, disparity maps, multiplane images or even voxel grids, they represent the scene as a continuous volume, with volumetric parameters like view-dependent radiance and volume density obtained by querying a neural network. The NeRF representation has now been widely used, with thousands of papers extending or building on it every year, multiple authors and websites providing overviews and surveys, and numerous industrial applications and startup companies. In this article, we briefly review the NeRF representation, and describe the three decades-long quest to find the best 3D representation for view synthesis and related problems, culminating in the NeRF papers. We then describe new developments in terms of NeRF representations and make some observations and insights regarding the future of 3D representations. △ Less

Submitted 18 August, 2023; v1 submitted 4 August, 2023; originally announced August 2023.

Comments: Updated based on feedback in-person and via e-mail at SIGGRAPH 2023. In particular, I have added references and discussion of seminal SIGGRAPH image-based rendering papers, and better put the recent Kerbl et al. work in context, with more references

Neural Free-Viewpoint Relighting for Glossy Indirect Illumination

Authors: Nithin Raghavan, Yan Xiao, Kai-En Lin, Tiancheng Sun, Sai Bi, Zexiang Xu, Tzu-Mao Li, Ravi Ramamoorthi

Abstract: Precomputed Radiance Transfer (PRT) remains an attractive solution for real-time rendering of complex light transport effects such as glossy global illumination. After precomputation, we can relight the scene with new environment maps while changing viewpoint in real-time. However, practical PRT methods are usually limited to low-frequency spherical harmonic lighting. All-frequency techniques usin… ▽ More Precomputed Radiance Transfer (PRT) remains an attractive solution for real-time rendering of complex light transport effects such as glossy global illumination. After precomputation, we can relight the scene with new environment maps while changing viewpoint in real-time. However, practical PRT methods are usually limited to low-frequency spherical harmonic lighting. All-frequency techniques using wavelets are promising but have so far had little practical impact. The curse of dimensionality and much higher data requirements have typically limited them to relighting with fixed view or only direct lighting with triple product integrals. In this paper, we demonstrate a hybrid neural-wavelet PRT solution to high-frequency indirect illumination, including glossy reflection, for relighting with changing view. Specifically, we seek to represent the light transport function in the Haar wavelet basis. For global illumination, we learn the wavelet transport using a small multi-layer perceptron (MLP) applied to a feature field as a function of spatial location and wavelet index, with reflected direction and material parameters being other MLP inputs. We optimize/learn the feature field (compactly represented by a tensor decomposition) and MLP parameters from multiple images of the scene under different lighting and viewing conditions. We demonstrate real-time (512 x 512 at 24 FPS, 800 x 600 at 13 FPS) precomputed rendering of challenging scenes involving view-dependent reflections and even caustics. △ Less

Submitted 12 July, 2023; originally announced July 2023.

Comments: 13 pages, 9 figures, to appear in cgf proceedings of egsr 2023

PVP: Personalized Video Prior for Editable Dynamic Portraits using StyleGAN

Authors: Kai-En Lin, Alex Trevithick, Keli Cheng, Michel Sarkis, Mohsen Ghafoorian, Ning Bi, Gerhard Reitmayr, Ravi Ramamoorthi

Abstract: Portrait synthesis creates realistic digital avatars which enable users to interact with others in a compelling way. Recent advances in StyleGAN and its extensions have shown promising results in synthesizing photorealistic and accurate reconstruction of human faces. However, previous methods often focus on frontal face synthesis and most methods are not able to handle large head rotations due to… ▽ More Portrait synthesis creates realistic digital avatars which enable users to interact with others in a compelling way. Recent advances in StyleGAN and its extensions have shown promising results in synthesizing photorealistic and accurate reconstruction of human faces. However, previous methods often focus on frontal face synthesis and most methods are not able to handle large head rotations due to the training data distribution of StyleGAN. In this work, our goal is to take as input a monocular video of a face, and create an editable dynamic portrait able to handle extreme head poses. The user can create novel viewpoints, edit the appearance, and animate the face. Our method utilizes pivotal tuning inversion (PTI) to learn a personalized video prior from a monocular video sequence. Then we can input pose and expression coefficients to MLPs and manipulate the latent vectors to synthesize different viewpoints and expressions of the subject. We also propose novel loss functions to further disentangle pose and expression in the latent space. Our algorithm shows much better performance over previous approaches on monocular video datasets, and it is also capable of running in real-time at 54 FPS on an RTX 3080. △ Less

Submitted 29 June, 2023; originally announced June 2023.

Comments: Project website: https://cseweb.ucsd.edu//~viscomp/projects/EGSR23PVP/

Real-Time Radiance Fields for Single-Image Portrait View Synthesis

Authors: Alex Trevithick, Matthew Chan, Michael Stengel, Eric R. Chan, Chao Liu, Zhiding Yu, Sameh Khamis, Manmohan Chandraker, Ravi Ramamoorthi, Koki Nagano

Abstract: We present a one-shot method to infer and render a photorealistic 3D representation from a single unposed image (e.g., face portrait) in real-time. Given a single RGB input, our image encoder directly predicts a canonical triplane representation of a neural radiance field for 3D-aware novel view synthesis via volume rendering. Our method is fast (24 fps) on consumer hardware, and produces higher q… ▽ More We present a one-shot method to infer and render a photorealistic 3D representation from a single unposed image (e.g., face portrait) in real-time. Given a single RGB input, our image encoder directly predicts a canonical triplane representation of a neural radiance field for 3D-aware novel view synthesis via volume rendering. Our method is fast (24 fps) on consumer hardware, and produces higher quality results than strong GAN-inversion baselines that require test-time optimization. To train our triplane encoder pipeline, we use only synthetic data, showing how to distill the knowledge from a pretrained 3D GAN into a feedforward encoder. Technical contributions include a Vision Transformer-based triplane encoder, a camera data augmentation strategy, and a well-designed loss function for synthetic data training. We benchmark against the state-of-the-art methods, demonstrating significant improvements in robustness and image quality in challenging real-world settings. We showcase our results on portraits of faces (FFHQ) and cats (AFHQ), but our algorithm can also be applied in the future to other categories with a 3D-aware image generator. △ Less

Submitted 3 May, 2023; originally announced May 2023.

Comments: Project page: https://research.nvidia.com/labs/nxp/lp3d/

Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation

Authors: Liwen Wu, Rui Zhu, Mustafa B. Yaldiz, Yinhao Zhu, Hong Cai, Janarbek Matai, Fatih Porikli, Tzu-Mao Li, Manmohan Chandraker, Ravi Ramamoorthi

Abstract: Inverse path tracing has recently been applied to joint material and lighting estimation, given geometry and multi-view HDR observations of an indoor scene. However, it has two major limitations: path tracing is expensive to compute, and ambiguities exist between reflection and emission. Our Factorized Inverse Path Tracing (FIPT) addresses these challenges by using a factored light transport formu… ▽ More Inverse path tracing has recently been applied to joint material and lighting estimation, given geometry and multi-view HDR observations of an indoor scene. However, it has two major limitations: path tracing is expensive to compute, and ambiguities exist between reflection and emission. Our Factorized Inverse Path Tracing (FIPT) addresses these challenges by using a factored light transport formulation and finds emitters driven by rendering errors. Our algorithm enables accurate material and lighting optimization faster than previous work, and is more effective at resolving ambiguities. The exhaustive experiments on synthetic scenes show that our method (1) outperforms state-of-the-art indoor inverse rendering and relighting methods particularly in the presence of complex illumination effects; (2) speeds up inverse path tracing optimization to less than an hour. We further demonstrate robustness to noisy inputs through material and lighting estimates that allow plausible relighting in a real scene. The source code is available at: https://github.com/lwwu2/fipt △ Less

Submitted 23 August, 2023; v1 submitted 12 April, 2023; originally announced April 2023.

Comments: Updated experiment results; modified real-world sections

Importance Sampling BRDF Derivatives

Authors: Yash Belhe, Bing Xu, Sai Praveen Bangaru, Ravi Ramamoorthi, Tzu-Mao Li

Abstract: We propose a set of techniques to efficiently importance sample the derivatives of several BRDF models. In differentiable rendering, BRDFs are replaced by their differential BRDF counterparts which are real-valued and can have negative values. This leads to a new source of variance arising from their change in sign. Real-valued functions cannot be perfectly importance sampled by a positive-valued… ▽ More We propose a set of techniques to efficiently importance sample the derivatives of several BRDF models. In differentiable rendering, BRDFs are replaced by their differential BRDF counterparts which are real-valued and can have negative values. This leads to a new source of variance arising from their change in sign. Real-valued functions cannot be perfectly importance sampled by a positive-valued PDF and the direct application of BRDF sampling leads to high variance. Previous attempts at antithetic sampling only addressed the derivative with the roughness parameter of isotropic microfacet BRDFs. Our work generalizes BRDF derivative sampling to anisotropic microfacet models, mixture BRDFs, Oren-Nayar, Hanrahan-Krueger, among other analytic BRDFs. Our method first decomposes the real-valued differential BRDF into a sum of single-signed functions, eliminating variance from a change in sign. Next, we importance sample each of the resulting single-signed functions separately. The first decomposition, positivization, partitions the real-valued function based on its sign, and is effective at variance reduction when applicable. However, it requires analytic knowledge of the roots of the differential BRDF, and for it to be analytically integrable too. Our key insight is that the single-signed functions can have overlapping support, which significantly broadens the ways we can decompose a real-valued function. Our product and mixture decompositions exploit this property, and they allow us to support several BRDF derivatives that positivization could not handle. For a wide variety of BRDF derivatives, our method significantly reduces the variance (up to 58x in some cases) at equal computation cost and enables better recovery of spatially varying textures through gradient-descent-based inverse rendering. △ Less

Submitted 8 April, 2023; originally announced April 2023.

A Generalized Ray Formulation For Wave-Optics Rendering

Authors: Shlomi Steinberg, Ravi Ramamoorthi, Benedikt Bitterli, Eugene d'Eon, Ling-Qi Yan, Matt Pharr

Abstract: Under ray-optical light transport, the classical ray serves as a linear and local "point query" of light's behaviour. Linearity and locality are crucial to the formulation of sophisticated path tracing and sampling techniques, that enable efficient solutions to light transport problems in complex, real-world settings and environments. However, such formulations are firmly confined to the realm of… ▽ More Under ray-optical light transport, the classical ray serves as a linear and local "point query" of light's behaviour. Linearity and locality are crucial to the formulation of sophisticated path tracing and sampling techniques, that enable efficient solutions to light transport problems in complex, real-world settings and environments. However, such formulations are firmly confined to the realm of ray optics, while many applications of interest -- in computer graphics and computational optics -- demand a more precise understanding of light: as waves. We rigorously formulate the generalized ray, which enables linear and weakly-local queries of arbitrary wave-optical distributions of light. Generalized rays arise from photodetection states, and therefore allow performing backward (sensor-to-source) wave-optical light transport. Our formulations are accurate and highly general: they facilitate the application of modern path tracing techniques for wave-optical rendering, with light of any state of coherence and any spectral properties. We improve upon the state-of-the-art in terms of the generality and accuracy of the formalism, ease of application, as well as performance. As a consequence, we are able to render large, complex scenes, as in Fig. 1, and even do interactive wave-optical light transport, none of which is possible with any existing method. We numerically validate our formalism, and make connection to partially-coherent light transport. △ Less

Submitted 7 January, 2024; v1 submitted 28 March, 2023; originally announced March 2023.

Comments: For additional information, see https://ssteinberg.xyz/2023/03/27/rtplt/

NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion

Authors: Jiatao Gu, Alex Trevithick, Kai-En Lin, Josh Susskind, Christian Theobalt, Lingjie Liu, Ravi Ramamoorthi

Abstract: Novel view synthesis from a single image requires inferring occluded regions of objects and scenes whilst simultaneously maintaining semantic and physical consistency with the input. Existing approaches condition neural radiance fields (NeRF) on local image features, projecting points to the input image plane, and aggregating 2D features to perform volume rendering. However, under severe occlusion… ▽ More Novel view synthesis from a single image requires inferring occluded regions of objects and scenes whilst simultaneously maintaining semantic and physical consistency with the input. Existing approaches condition neural radiance fields (NeRF) on local image features, projecting points to the input image plane, and aggregating 2D features to perform volume rendering. However, under severe occlusion, this projection fails to resolve uncertainty, resulting in blurry renderings that lack details. In this work, we propose NerfDiff, which addresses this issue by distilling the knowledge of a 3D-aware conditional diffusion model (CDM) into NeRF through synthesizing and refining a set of virtual views at test time. We further propose a novel NeRF-guided distillation algorithm that simultaneously generates 3D consistent virtual views from the CDM samples, and finetunes the NeRF based on the improved virtual views. Our approach significantly outperforms existing NeRF-based and geometry-free approaches on challenging datasets, including ShapeNet, ABO, and Clevr3D. △ Less

Submitted 20 February, 2023; originally announced February 2023.

Comments: Project page: https://jiataogu.me/nerfdiff/

Decorrelating ReSTIR Samplers via MCMC Mutations

Authors: Rohan Sawhney, Daqi Lin, Markus Kettunen, Benedikt Bitterli, Ravi Ramamoorthi, Chris Wyman, Matt Pharr

Abstract: Monte Carlo rendering algorithms often utilize correlations between pixels to improve efficiency and enhance image quality. For real-time applications in particular, repeated reservoir resampling offers a powerful framework to reuse samples both spatially in an image and temporally across multiple frames. While such techniques achieve equal-error up to 100 times faster for real-time direct lightin… ▽ More Monte Carlo rendering algorithms often utilize correlations between pixels to improve efficiency and enhance image quality. For real-time applications in particular, repeated reservoir resampling offers a powerful framework to reuse samples both spatially in an image and temporally across multiple frames. While such techniques achieve equal-error up to 100 times faster for real-time direct lighting and global illumination, they are still far from optimal. For instance, unchecked spatiotemporal resampling often introduces noticeable correlation artifacts, while reservoirs holding more than one sample suffer from impoverishment in the form of duplicate samples. We demonstrate how interleaving Markov Chain Monte Carlo (MCMC) mutations with reservoir resampling helps alleviate these issues, especially in scenes with glossy materials and difficult-to-sample lighting. Moreover, our approach does not introduce any bias, and in practice we find considerable improvement in image quality with just a single mutation per reservoir sample in each frame. △ Less

Submitted 31 October, 2022; originally announced November 2022.

Vision Transformer for NeRF-Based View Synthesis from a Single Input Image

Authors: Kai-En Lin, Lin Yen-Chen, Wei-Sheng Lai, Tsung-Yi Lin, Yi-Chang Shih, Ravi Ramamoorthi

Abstract: Although neural radiance fields (NeRF) have shown impressive advances for novel view synthesis, most methods typically require multiple input images of the same scene with accurate camera poses. In this work, we seek to substantially reduce the inputs to a single unposed image. Existing approaches condition on local image features to reconstruct a 3D object, but often render blurry predictions at… ▽ More Although neural radiance fields (NeRF) have shown impressive advances for novel view synthesis, most methods typically require multiple input images of the same scene with accurate camera poses. In this work, we seek to substantially reduce the inputs to a single unposed image. Existing approaches condition on local image features to reconstruct a 3D object, but often render blurry predictions at viewpoints that are far away from the source view. To address this issue, we propose to leverage both the global and local features to form an expressive 3D representation. The global features are learned from a vision transformer, while the local features are extracted from a 2D convolutional network. To synthesize a novel view, we train a multilayer perceptron (MLP) network conditioned on the learned 3D representation to perform volume rendering. This novel 3D representation allows the network to reconstruct unseen regions without enforcing constraints like symmetry or canonical coordinate systems. Our method can render novel views from only a single input image and generalize across multiple object categories using a single model. Quantitative and qualitative evaluations demonstrate that the proposed method achieves state-of-the-art performance and renders richer details than existing approaches. △ Less

Submitted 13 October, 2022; v1 submitted 12 July, 2022; originally announced July 2022.

Comments: WACV 2023 Project website: https://cseweb.ucsd.edu/~viscomp/projects/VisionNeRF/

Physically-Based Editing of Indoor Scene Lighting from a Single Image

Authors: Zhengqin Li, Jia Shi, Sai Bi, Rui Zhu, Kalyan Sunkavalli, Miloš Hašan, Zexiang Xu, Ravi Ramamoorthi, Manmohan Chandraker

Abstract: We present a method to edit complex indoor lighting from a single image with its predicted depth and light source segmentation masks. This is an extremely challenging problem that requires modeling complex light transport, and disentangling HDR lighting from material and geometry with only a partial LDR observation of the scene. We tackle this problem using two novel components: 1) a holistic scen… ▽ More We present a method to edit complex indoor lighting from a single image with its predicted depth and light source segmentation masks. This is an extremely challenging problem that requires modeling complex light transport, and disentangling HDR lighting from material and geometry with only a partial LDR observation of the scene. We tackle this problem using two novel components: 1) a holistic scene reconstruction method that estimates scene reflectance and parametric 3D lighting, and 2) a neural rendering framework that re-renders the scene from our predictions. We use physically-based indoor light representations that allow for intuitive editing, and infer both visible and invisible light sources. Our neural rendering framework combines physically-based direct illumination and shadow rendering with deep networks to approximate global illumination. It can capture challenging lighting effects, such as soft shadows, directional lighting, specular materials, and interreflections. Previous single image inverse rendering methods usually entangle scene lighting and geometry and only support applications like object insertion. Instead, by combining parametric 3D lighting estimation with neural scene rendering, we demonstrate the first automatic method to achieve full scene relighting, including light source insertion, removal, and replacement, from a single image. All source code and data will be publicly released. △ Less

Submitted 23 July, 2022; v1 submitted 19 May, 2022; originally announced May 2022.

A Level Set Theory for Neural Implicit Evolution under Explicit Flows

Authors: Ishit Mehta, Manmohan Chandraker, Ravi Ramamoorthi

Abstract: Coordinate-based neural networks parameterizing implicit surfaces have emerged as efficient representations of geometry. They effectively act as parametric level sets with the zero-level set defining the surface of interest. We present a framework that allows applying deformation operations defined for triangle meshes onto such implicit surfaces. Several of these operations can be viewed as energy… ▽ More Coordinate-based neural networks parameterizing implicit surfaces have emerged as efficient representations of geometry. They effectively act as parametric level sets with the zero-level set defining the surface of interest. We present a framework that allows applying deformation operations defined for triangle meshes onto such implicit surfaces. Several of these operations can be viewed as energy-minimization problems that induce an instantaneous flow field on the explicit surface. Our method uses the flow field to deform parametric implicit surfaces by extending the classical theory of level sets. We also derive a consolidated view for existing methods on differentiable surface extraction and rendering, by formalizing connections to the level-set theory. We show that these methods drift from the theory and that our approach exhibits improvements for applications like surface smoothing, mean-curvature flow, inverse rendering and user-defined editing on implicit geometry. △ Less

Submitted 21 July, 2022; v1 submitted 14 April, 2022; originally announced April 2022.

Comments: ECCV 2022 (Oral); Project Page at https://ishit.github.io/nie

Scalar Spatiotemporal Blue Noise Masks

Authors: Alan Wolfe, Nathan Morrical, Tomas Akenine-Möller, Ravi Ramamoorthi

Abstract: Blue noise error patterns are well suited to human perception, and when applied to stochastic rendering techniques, blue noise masks (blue noise textures) minimize unwanted low-frequency noise in the final image. Current methods of applying blue noise masks at each frame independently produce white noise frequency spectra temporally. This white noise results in slower integration convergence over… ▽ More Blue noise error patterns are well suited to human perception, and when applied to stochastic rendering techniques, blue noise masks (blue noise textures) minimize unwanted low-frequency noise in the final image. Current methods of applying blue noise masks at each frame independently produce white noise frequency spectra temporally. This white noise results in slower integration convergence over time and unstable results when filtered temporally. Unfortunately, achieving temporally stable blue noise distributions is non-trivial since 3D blue noise does not exhibit the desired 2D blue noise properties, and alternative approaches degrade the spatial blue noise qualities. We propose novel blue noise patterns that, when animated, produce values at a pixel that are well distributed over time, converge rapidly for Monte Carlo integration, and are more stable under TAA, while still retaining spatial blue noise properties. To do so, we propose an extension to the well-known void and cluster algorithm that reformulates the underlying energy function to produce spatiotemporal blue noise masks. These masks exhibit blue noise frequency spectra in both the spatial and temporal domains, resulting in visually pleasing error patterns, rapid convergence speeds, and increased stability when filtered temporally. We demonstrate these improvements on a variety of applications, including dithering, stochastic transparency, ambient occlusion, and volumetric rendering. By extending spatial blue noise to spatiotemporal blue noise, we overcome the convergence limitations of prior blue noise works, enabling new applications for blue noise distributions. △ Less

Submitted 17 December, 2021; originally announced December 2021.

ACM Class: I.3.3; I.3.7

Journal ref: Eurographics Symposium on Rendering (EGSR), pp. 117-126 (2022)

Learning Neural Transmittance for Efficient Rendering of Reflectance Fields

Authors: Mohammad Shafiei, Sai Bi, Zhengqin Li, Aidas Liaudanskas, Rodrigo Ortiz-Cayon, Ravi Ramamoorthi

Abstract: Recently neural volumetric representations such as neural reflectance fields have been widely applied to faithfully reproduce the appearance of real-world objects and scenes under novel viewpoints and lighting conditions. However, it remains challenging and time-consuming to render such representations under complex lighting such as environment maps, which requires individual ray marching towards… ▽ More Recently neural volumetric representations such as neural reflectance fields have been widely applied to faithfully reproduce the appearance of real-world objects and scenes under novel viewpoints and lighting conditions. However, it remains challenging and time-consuming to render such representations under complex lighting such as environment maps, which requires individual ray marching towards each single light to calculate the transmittance at every sampled point. In this paper, we propose a novel method based on precomputed Neural Transmittance Functions to accelerate the rendering of neural reflectance fields. Our neural transmittance functions enable us to efficiently query the transmittance at an arbitrary point in space along an arbitrary ray without tedious ray marching, which effectively reduces the time-complexity of the rendering. We propose a novel formulation for the neural transmittance function, and train it jointly with the neural reflectance fields on images captured under collocated camera and light, while enforcing monotonicity. Results on real and synthetic scenes demonstrate almost two order of magnitude speedup for renderings under environment maps with minimal accuracy loss. △ Less

Submitted 25 October, 2021; originally announced October 2021.

View Synthesis of Dynamic Scenes based on Deep 3D Mask Volume

Authors: Kai-En Lin, Guowei Yang, Lei Xiao, Feng Liu, Ravi Ramamoorthi

Abstract: Image view synthesis has seen great success in reconstructing photorealistic visuals, thanks to deep learning and various novel representations. The next key step in immersive virtual experiences is view synthesis of dynamic scenes. However, several challenges exist due to the lack of high-quality training datasets, and the additional time dimension for videos of dynamic scenes. To address this is… ▽ More Image view synthesis has seen great success in reconstructing photorealistic visuals, thanks to deep learning and various novel representations. The next key step in immersive virtual experiences is view synthesis of dynamic scenes. However, several challenges exist due to the lack of high-quality training datasets, and the additional time dimension for videos of dynamic scenes. To address this issue, we introduce a multi-view video dataset, captured with a custom 10-camera rig in 120FPS. The dataset contains 96 high-quality scenes showing various visual effects and human interactions in outdoor scenes. We develop a new algorithm, Deep 3D Mask Volume, which enables temporally-stable view extrapolation from binocular videos of dynamic scenes, captured by static cameras. Our algorithm addresses the temporal inconsistency of disocclusions by identifying the error-prone areas with a 3D mask volume, and replaces them with static background observed throughout the video. Our method enables manipulation in 3D space as opposed to simple 2D masks, We demonstrate better temporal stability than frame-by-frame static view synthesis methods, or those that use 2D masks. The resulting view synthesis videos show minimal flickering artifacts and allow for larger translational movements. △ Less

Submitted 28 November, 2022; v1 submitted 30 August, 2021; originally announced August 2021.

Comments: This is the extended version of the paper published at ICCV 2021. Code and dataset available at: https://cseweb.ucsd.edu//~viscomp/projects/ICCV21Deep/

NeLF: Neural Light-transport Field for Portrait View Synthesis and Relighting

Authors: Tiancheng Sun, Kai-En Lin, Sai Bi, Zexiang Xu, Ravi Ramamoorthi

Abstract: Human portraits exhibit various appearances when observed from different views under different lighting conditions. We can easily imagine how the face will look like in another setup, but computer algorithms still fail on this problem given limited observations. To this end, we present a system for portrait view synthesis and relighting: given multiple portraits, we use a neural network to predict… ▽ More Human portraits exhibit various appearances when observed from different views under different lighting conditions. We can easily imagine how the face will look like in another setup, but computer algorithms still fail on this problem given limited observations. To this end, we present a system for portrait view synthesis and relighting: given multiple portraits, we use a neural network to predict the light-transport field in 3D space, and from the predicted Neural Light-transport Field (NeLF) produce a portrait from a new camera view under a new environmental lighting. Our system is trained on a large number of synthetic models, and can generalize to different synthetic and real portraits under various lighting conditions. Our method achieves simultaneous view synthesis and relighting given multi-view portraits as the input, and achieves state-of-the-art results. △ Less

Submitted 26 July, 2021; originally announced July 2021.

Comments: Published at EGSR 2021. Project page with video and code: http://cseweb.ucsd.edu/~viscomp/projects/EGSR21NeLF/

Modulated Periodic Activations for Generalizable Local Functional Representations

Authors: Ishit Mehta, Michaël Gharbi, Connelly Barnes, Eli Shechtman, Ravi Ramamoorthi, Manmohan Chandraker

Abstract: Multi-Layer Perceptrons (MLPs) make powerful functional representations for sampling and reconstruction problems involving low-dimensional signals like images,shapes and light fields. Recent works have significantly improved their ability to represent high-frequency content by using periodic activations or positional encodings. This often came at the expense of generalization: modern methods are t… ▽ More Multi-Layer Perceptrons (MLPs) make powerful functional representations for sampling and reconstruction problems involving low-dimensional signals like images,shapes and light fields. Recent works have significantly improved their ability to represent high-frequency content by using periodic activations or positional encodings. This often came at the expense of generalization: modern methods are typically optimized for a single signal. We present a new representation that generalizes to multiple instances and achieves state-of-the-art fidelity. We use a dual-MLP architecture to encode the signals. A synthesis network creates a functional mapping from a low-dimensional input (e.g. pixel-position) to the output domain (e.g. RGB color). A modulation network maps a latent code corresponding to the target signal to parameters that modulate the periodic activations of the synthesis network. We also propose a local-functional representation which enables generalization. The signal's domain is partitioned into a regular grid,with each tile represented by a latent code. At test time, the signal is encoded with high-fidelity by inferring (or directly optimizing) the latent code-book. Our approach produces generalizable functional representations of images, videos and shapes, and achieves higher reconstruction quality than prior works that are optimized for a single signal. △ Less

Submitted 8 April, 2021; originally announced April 2021.

Comments: Project Page at https://ishit.github.io/modsine/

NeuMIP: Multi-Resolution Neural Materials

Authors: Alexandr Kuznetsov, Krishna Mullia, Zexiang Xu, Miloš Hašan, Ravi Ramamoorthi

Abstract: We propose NeuMIP, a neural method for representing and rendering a variety of material appearances at different scales. Classical prefiltering (mipmapping) methods work well on simple material properties such as diffuse color, but fail to generalize to normals, self-shadowing, fibers or more complex microstructures and reflectances. In this work, we generalize traditional mipmap pyramids to pyram… ▽ More We propose NeuMIP, a neural method for representing and rendering a variety of material appearances at different scales. Classical prefiltering (mipmapping) methods work well on simple material properties such as diffuse color, but fail to generalize to normals, self-shadowing, fibers or more complex microstructures and reflectances. In this work, we generalize traditional mipmap pyramids to pyramids of neural textures, combined with a fully connected network. We also introduce neural offsets, a novel method which allows rendering materials with intricate parallax effects without any tessellation. This generalizes classical parallax mapping, but is trained without supervision by any explicit heightfield. Neural materials within our system support a 7-dimensional query, including position, incoming and outgoing direction, and the desired filter kernel size. The materials have small storage (on the order of standard mipmapping except with more texture channels), and can be integrated within common Monte-Carlo path tracing systems. We demonstrate our method on a variety of materials, resulting in complex appearance across levels of detail, with accurate parallax, self-shadowing, and other effects. △ Less

Submitted 6 April, 2021; originally announced April 2021.

Light Stage Super-Resolution: Continuous High-Frequency Relighting

Authors: Tiancheng Sun, Zexiang Xu, Xiuming Zhang, Sean Fanello, Christoph Rhemann, Paul Debevec, Yun-Ta Tsai, Jonathan T. Barron, Ravi Ramamoorthi

Abstract: The light stage has been widely used in computer graphics for the past two decades, primarily to enable the relighting of human faces. By capturing the appearance of the human subject under different light sources, one obtains the light transport matrix of that subject, which enables image-based relighting in novel environments. However, due to the finite number of lights in the stage, the light t… ▽ More The light stage has been widely used in computer graphics for the past two decades, primarily to enable the relighting of human faces. By capturing the appearance of the human subject under different light sources, one obtains the light transport matrix of that subject, which enables image-based relighting in novel environments. However, due to the finite number of lights in the stage, the light transport matrix only represents a sparse sampling on the entire sphere. As a consequence, relighting the subject with a point light or a directional source that does not coincide exactly with one of the lights in the stage requires interpolation and resampling the images corresponding to nearby lights, and this leads to ghosting shadows, aliased specularities, and other artifacts. To ameliorate these artifacts and produce better results under arbitrary high-frequency lighting, this paper proposes a learning-based solution for the "super-resolution" of scans of human faces taken from a light stage. Given an arbitrary "query" light direction, our method aggregates the captured images corresponding to neighboring lights in the stage, and uses a neural network to synthesize a rendering of the face that appears to be illuminated by a "virtual" light source at the query location. This neural network must circumvent the inherent aliasing and regularity of the light stage data that was used for training, which we accomplish through the use of regularized traditional interpolation methods within our network. Our learned model is able to produce renderings for arbitrary light directions that exhibit realistic shadows and specular highlights, and is able to generalize across a wide variety of subjects. △ Less

Submitted 17 October, 2020; originally announced October 2020.

Comments: Siggraph Asia 2020

Photon-Driven Neural Path Guiding

Authors: Shilin Zhu, Zexiang Xu, Tiancheng Sun, Alexandr Kuznetsov, Mark Meyer, Henrik Wann Jensen, Hao Su, Ravi Ramamoorthi

Abstract: Although Monte Carlo path tracing is a simple and effective algorithm to synthesize photo-realistic images, it is often very slow to converge to noise-free results when involving complex global illumination. One of the most successful variance-reduction techniques is path guiding, which can learn better distributions for importance sampling to reduce pixel noise. However, previous methods require… ▽ More Although Monte Carlo path tracing is a simple and effective algorithm to synthesize photo-realistic images, it is often very slow to converge to noise-free results when involving complex global illumination. One of the most successful variance-reduction techniques is path guiding, which can learn better distributions for importance sampling to reduce pixel noise. However, previous methods require a large number of path samples to achieve reliable path guiding. We present a novel neural path guiding approach that can reconstruct high-quality sampling distributions for path guiding from a sparse set of samples, using an offline trained neural network. We leverage photons traced from light sources as the input for sampling density reconstruction, which is highly effective for challenging scenes with strong global illumination. To fully make use of our deep neural network, we partition the scene space into an adaptive hierarchical grid, in which we apply our network to reconstruct high-quality sampling distributions for any local region in the scene. This allows for highly efficient path guiding for any path bounce at any location in path tracing. We demonstrate that our photon-driven neural path guiding method can generalize well on diverse challenging testing scenes that are not seen in training. Our approach achieves significantly better rendering results of testing scenes than previous state-of-the-art path guiding methods. △ Less

Submitted 5 October, 2020; originally announced October 2020.

Comments: Keywords: computer graphics, rendering, path tracing, path guiding, machine learning, neural networks, denoising, reconstruction