Showing 1–26 of 26 results for author: Zhe, X

Realistic Curriculum Reinforcement Learning for Autonomous and Sustainable Marine Vessel Navigation

Authors: Zhang Xiaocai, Xiao Zhe, Liang Maohan, Liu Tao, Li Haijiang, Zhang Wenbin

Abstract: Sustainability is becoming increasingly critical in the maritime transport, encompassing both environmental and social impacts, such as Greenhouse Gas (GHG) emissions and navigational safety. Traditional vessel navigation heavily relies on human experience, often lacking autonomy and emission awareness, and is prone to human errors that may compromise safety. In this paper, we propose a Curriculum… ▽ More Sustainability is becoming increasingly critical in the maritime transport, encompassing both environmental and social impacts, such as Greenhouse Gas (GHG) emissions and navigational safety. Traditional vessel navigation heavily relies on human experience, often lacking autonomy and emission awareness, and is prone to human errors that may compromise safety. In this paper, we propose a Curriculum Reinforcement Learning (CRL) framework integrated with a realistic, data-driven marine simulation environment and a machine learning-based fuel consumption prediction module. The simulation environment is constructed using real-world vessel movement data and enhanced with a Diffusion Model to simulate dynamic maritime conditions. Vessel fuel consumption is estimated using historical operational data and learning-based regression. The surrounding environment is represented as image-based inputs to capture spatial complexity. We design a lightweight, policy-based CRL agent with a comprehensive reward mechanism that considers safety, emissions, timeliness, and goal completion. This framework effectively handles complex tasks progressively while ensuring stable and efficient learning in continuous action spaces. We validate the proposed approach in a sea area of the Indian Ocean, demonstrating its efficacy in enabling sustainable and safe vessel navigation. △ Less

Submitted 15 January, 2026; originally announced January 2026.

Comments: Present in The 40th Annual AAAI Conference on Artificial Intelligence (AAAI-26)

HunyuanVideo 1.5 Technical Report

Authors: Bing Wu, Chang Zou, Changlin Li, Duojun Huang, Fang Yang, Hao Tan, Jack Peng, Jianbing Wu, Jiangfeng Xiong, Jie Jiang, Linus, Patrol, Peizhen Zhang, Peng Chen, Penghao Zhao, Qi Tian, Songtao Liu, Weijie Kong, Weiyan Wang, Xiao He, Xin Li, Xinchi Deng, Xuefei Zhe, Yang Li, Yanxin Long , et al. (56 additional authors not shown)

Abstract: We present HunyuanVideo 1.5, a lightweight yet powerful open-source video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture featuring selective and sliding til… ▽ More We present HunyuanVideo 1.5, a lightweight yet powerful open-source video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture featuring selective and sliding tile attention (SSTA), enhanced bilingual understanding through glyph-aware text encoding, progressive pre-training and post-training, and an efficient video super-resolution network. Leveraging these designs, we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions. Extensive experiments demonstrate that this compact and proficient model establishes a new state-of-the-art among open-source video generation models. By releasing the code and model weights, we provide the community with a high-performance foundation that lowers the barrier to video creation and research, making advanced video generation accessible to a broader audience. All open-source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5. △ Less

Submitted 24 November, 2025; v1 submitted 24 November, 2025; originally announced November 2025.

Towards Fine-Grained Human Motion Video Captioning

Authors: Guorui Song, Guocun Wang, Zhe Huang, Jing Lin, Xuefei Zhe, Jian Li, Haoqian Wang

Abstract: Generating accurate descriptions of human actions in videos remains a challenging task for video captioning models. Existing approaches often struggle to capture fine-grained motion details, resulting in vague or semantically inconsistent captions. In this work, we introduce the Motion-Augmented Caption Model (M-ACM), a novel generative framework that enhances caption quality by incorporating moti… ▽ More Generating accurate descriptions of human actions in videos remains a challenging task for video captioning models. Existing approaches often struggle to capture fine-grained motion details, resulting in vague or semantically inconsistent captions. In this work, we introduce the Motion-Augmented Caption Model (M-ACM), a novel generative framework that enhances caption quality by incorporating motion-aware decoding. At its core, M-ACM leverages motion representations derived from human mesh recovery to explicitly highlight human body dynamics, thereby reducing hallucinations and improving both semantic fidelity and spatial alignment in the generated captions. To support research in this area, we present the Human Motion Insight (HMI) Dataset, comprising 115K video-description pairs focused on human movement, along with HMI-Bench, a dedicated benchmark for evaluating motion-focused video captioning. Experimental results demonstrate that M-ACM significantly outperforms previous methods in accurately describing complex human motions and subtle temporal variations, setting a new standard for motion-centric video captioning. △ Less

Submitted 24 October, 2025; originally announced October 2025.

HunyuanImage 3.0 Technical Report

Authors: Siyu Cao, Hangting Chen, Peng Chen, Yiji Cheng, Yutao Cui, Xinchi Deng, Ying Dong, Kipper Gong, Tianpeng Gu, Xiusen Gu, Tiankai Hang, Duojun Huang, Jie Jiang, Zhengkai Jiang, Weijie Kong, Changlin Li, Donghao Li, Junzhe Li, Xin Li, Yang Li, Zhenxi Li, Zhimin Li, Jiaxin Lin, Linus, Lucaz Liu , et al. (49 additional authors not shown)

Abstract: We present HunyuanImage 3.0, a native multimodal model that unifies multimodal understanding and generation within an autoregressive framework, with its image generation module publicly available. The achievement of HunyuanImage 3.0 relies on several key components, including meticulous data curation, advanced architecture design, a native Chain-of-Thoughts schema, progressive model pre-training,… ▽ More We present HunyuanImage 3.0, a native multimodal model that unifies multimodal understanding and generation within an autoregressive framework, with its image generation module publicly available. The achievement of HunyuanImage 3.0 relies on several key components, including meticulous data curation, advanced architecture design, a native Chain-of-Thoughts schema, progressive model pre-training, aggressive model post-training, and an efficient infrastructure that enables large-scale training and inference. With these advancements, we successfully trained a Mixture-of-Experts (MoE) model comprising over 80 billion parameters in total, with 13 billion parameters activated per token during inference, making it the largest and most powerful open-source image generative model to date. We conducted extensive experiments and the results of automatic and human evaluation of text-image alignment and visual quality demonstrate that HunyuanImage 3.0 rivals previous state-of-the-art models. By releasing the code and weights of HunyuanImage 3.0, we aim to enable the community to explore new ideas with a state-of-the-art foundation model, fostering a dynamic and vibrant multimodal ecosystem. All open source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanImage-3.0 △ Less

Submitted 2 February, 2026; v1 submitted 28 September, 2025; originally announced September 2025.

Bridging the Gap between Learning and Inference for Diffusion-Based Molecule Generation

Authors: Peidong Liu, Wenbo Zhang, Xue Zhe, Jiancheng Lv, Xianggen Liu

Abstract: The efficacy of diffusion models in generating a spectrum of data modalities, including images, text, and videos, has spurred inquiries into their utility in molecular generation, yielding significant advancements in the field. However, the molecular generation process with diffusion models involves multiple autoregressive steps over a finite time horizon, leading to exposure bias issues inherentl… ▽ More The efficacy of diffusion models in generating a spectrum of data modalities, including images, text, and videos, has spurred inquiries into their utility in molecular generation, yielding significant advancements in the field. However, the molecular generation process with diffusion models involves multiple autoregressive steps over a finite time horizon, leading to exposure bias issues inherently. To address the exposure bias issue, we propose a training framework named GapDiff. The core idea of GapDiff is to utilize model-predicted conformations as ground truth probabilistically during training, aiming to mitigate the data distributional disparity between training and inference, thereby enhancing the affinity of generated molecules. We conduct experiments using a 3D molecular generation model on the CrossDocked2020 dataset, and the vina energy and diversity demonstrate the potency of our framework with superior affinity. GapDiff is available at \url{https://github.com/HUGHNew/gapdiff}. △ Less

Submitted 8 November, 2024; originally announced November 2024.

Comments: 14 pages, 5 figures

Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview

Authors: Yanshu Wang, Tong Yang, Xiyan Liang, Guoan Wang, Hanning Lu, Xu Zhe, Yaoming Li, Li Weitao

Abstract: This paper provides a comprehensive overview of the principles, challenges, and methodologies associated with quantizing large-scale neural network models. As neural networks have evolved towards larger and more complex architectures to address increasingly sophisticated tasks, the computational and energy costs have escalated significantly. We explore the necessity and impact of model size growth… ▽ More This paper provides a comprehensive overview of the principles, challenges, and methodologies associated with quantizing large-scale neural network models. As neural networks have evolved towards larger and more complex architectures to address increasingly sophisticated tasks, the computational and energy costs have escalated significantly. We explore the necessity and impact of model size growth, highlighting the performance benefits as well as the computational challenges and environmental considerations. The core focus is on model quantization as a fundamental approach to mitigate these challenges by reducing model size and improving efficiency without substantially compromising accuracy. We delve into various quantization techniques, including both post-training quantization (PTQ) and quantization-aware training (QAT), and analyze several state-of-the-art algorithms such as LLM-QAT, PEQA(L4Q), ZeroQuant, SmoothQuant, and others. Through comparative analysis, we examine how these methods address issues like outliers, importance weighting, and activation quantization, ultimately contributing to more sustainable and accessible deployment of large-scale models. △ Less

Submitted 17 September, 2024; originally announced September 2024.

EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling

Authors: Haiyang Liu, Zihao Zhu, Giorgio Becherini, Yichen Peng, Mingyang Su, You Zhou, Xuefei Zhe, Naoya Iwamoto, Bo Zheng, Michael J. Black

Abstract: We propose EMAGE, a framework to generate full-body human gestures from audio and masked gestures, encompassing facial, local body, hands, and global movements. To achieve this, we first introduce BEAT2 (BEAT-SMPLX-FLAME), a new mesh-level holistic co-speech dataset. BEAT2 combines a MoShed SMPL-X body with FLAME head parameters and further refines the modeling of head, neck, and finger movements,… ▽ More We propose EMAGE, a framework to generate full-body human gestures from audio and masked gestures, encompassing facial, local body, hands, and global movements. To achieve this, we first introduce BEAT2 (BEAT-SMPLX-FLAME), a new mesh-level holistic co-speech dataset. BEAT2 combines a MoShed SMPL-X body with FLAME head parameters and further refines the modeling of head, neck, and finger movements, offering a community-standardized, high-quality 3D motion captured dataset. EMAGE leverages masked body gesture priors during training to boost inference performance. It involves a Masked Audio Gesture Transformer, facilitating joint training on audio-to-gesture generation and masked gesture reconstruction to effectively encode audio and body gesture hints. Encoded body hints from masked gestures are then separately employed to generate facial and body movements. Moreover, EMAGE adaptively merges speech features from the audio's rhythm and content and utilizes four compositional VQ-VAEs to enhance the results' fidelity and diversity. Experiments demonstrate that EMAGE generates holistic gestures with state-of-the-art performance and is flexible in accepting predefined spatial-temporal gesture inputs, generating complete, audio-synchronized results. Our code and dataset are available https://pantomatrix.github.io/EMAGE/ △ Less

Submitted 30 March, 2024; v1 submitted 30 December, 2023; originally announced January 2024.

Comments: Fix typos; Conflict of Interest Disclosure; CVPR Camera Ready; Project Page: https://pantomatrix.github.io/EMAGE/

Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry

Authors: Jiaxu Zhang, Junwu Weng, Di Kang, Fang Zhao, Shaoli Huang, Xuefei Zhe, Linchao Bao, Ying Shan, Jue Wang, Zhigang Tu

Abstract: A good motion retargeting cannot be reached without reasonable consideration of source-target differences on both the skeleton and shape geometry levels. In this work, we propose a novel Residual RETargeting network (R2ET) structure, which relies on two neural modification modules, to adjust the source motions to fit the target skeletons and shapes progressively. In particular, a skeleton-aware mo… ▽ More A good motion retargeting cannot be reached without reasonable consideration of source-target differences on both the skeleton and shape geometry levels. In this work, we propose a novel Residual RETargeting network (R2ET) structure, which relies on two neural modification modules, to adjust the source motions to fit the target skeletons and shapes progressively. In particular, a skeleton-aware module is introduced to preserve the source motion semantics. A shape-aware module is designed to perceive the geometries of target characters to reduce interpenetration and contact-missing. Driven by our explored distance-based losses that explicitly model the motion semantics and geometry, these two modules can learn residual motion modifications on the source motion to generate plausible retargeted motion in a single inference without post-processing. To balance these two modifications, we further present a balancing gate to conduct linear interpolation between them. Extensive experiments on the public dataset Mixamo demonstrate that our R2ET achieves the state-of-the-art performance, and provides a good balance between the preservation of motion semantics as well as the attenuation of interpenetration and contact-missing. Code is available at https://github.com/Kebii/R2ET. △ Less

Submitted 15 March, 2023; originally announced March 2023.

Comments: CVPR 2023

Audio2Gestures: Generating Diverse Gestures from Audio

Authors: Jing Li, Di Kang, Wenjie Pei, Xuefei Zhe, Ying Zhang, Linchao Bao, Zhenyu He

Abstract: People may perform diverse gestures affected by various mental and physical factors when speaking the same sentences. This inherent one-to-many relationship makes co-speech gesture generation from audio particularly challenging. Conventional CNNs/RNNs assume one-to-one mapping, and thus tend to predict the average of all possible target motions, easily resulting in plain/boring motions during infe… ▽ More People may perform diverse gestures affected by various mental and physical factors when speaking the same sentences. This inherent one-to-many relationship makes co-speech gesture generation from audio particularly challenging. Conventional CNNs/RNNs assume one-to-one mapping, and thus tend to predict the average of all possible target motions, easily resulting in plain/boring motions during inference. So we propose to explicitly model the one-to-many audio-to-motion mapping by splitting the cross-modal latent code into shared code and motion-specific code. The shared code is expected to be responsible for the motion component that is more correlated to the audio while the motion-specific code is expected to capture diverse motion information that is more independent of the audio. However, splitting the latent code into two parts poses extra training difficulties. Several crucial training losses/strategies, including relaxed motion loss, bicycle constraint, and diversity loss, are designed to better train the VAE. Experiments on both 3D and 2D motion datasets verify that our method generates more realistic and diverse motions than previous state-of-the-art methods, quantitatively and qualitatively. Besides, our formulation is compatible with discrete cosine transformation (DCT) modeling and other popular backbones (\textit{i.e.} RNN, Transformer). As for motion losses and quantitative motion evaluation, we find structured losses/metrics (\textit{e.g.} STFT) that consider temporal and/or spatial context complement the most commonly used point-wise losses (\textit{e.g.} PCK), resulting in better motion dynamics and more nuanced motion details. Finally, we demonstrate that our method can be readily used to generate motion sequences with user-specified motion clips on the timeline. △ Less

Submitted 16 January, 2023; originally announced January 2023.

Comments: arXiv admin note: substantial text overlap with arXiv:2108.06720

Learning Audio-Driven Viseme Dynamics for 3D Face Animation

Authors: Linchao Bao, Haoxian Zhang, Yue Qian, Tangli Xue, Changhai Chen, Xuefei Zhe, Di Kang

Abstract: We present a novel audio-driven facial animation approach that can generate realistic lip-synchronized 3D facial animations from the input audio. Our approach learns viseme dynamics from speech videos, produces animator-friendly viseme curves, and supports multilingual speech inputs. The core of our approach is a novel parametric viseme fitting algorithm that utilizes phoneme priors to extract vis… ▽ More We present a novel audio-driven facial animation approach that can generate realistic lip-synchronized 3D facial animations from the input audio. Our approach learns viseme dynamics from speech videos, produces animator-friendly viseme curves, and supports multilingual speech inputs. The core of our approach is a novel parametric viseme fitting algorithm that utilizes phoneme priors to extract viseme parameters from speech videos. With the guidance of phonemes, the extracted viseme curves can better correlate with phonemes, thus more controllable and friendly to animators. To support multilingual speech inputs and generalizability to unseen voices, we take advantage of deep audio feature models pretrained on multiple languages to learn the mapping from audio to viseme curves. Our audio-to-curves mapping achieves state-of-the-art performance even when the input audio suffers from distortions of volume, pitch, speed, or noise. Lastly, a viseme scanning approach for acquiring high-fidelity viseme assets is presented for efficient speech animation production. We show that the predicted viseme curves can be applied to different viseme-rigged characters to yield various personalized animations with realistic and natural facial motions. Our approach is artist-friendly and can be easily integrated into typical animation production workflows including blendshape or bone based animation. △ Less

Submitted 15 January, 2023; originally announced January 2023.

Comments: Project page: https://linchaobao.github.io/viseme2023/

CARD: Semantic Segmentation with Efficient Class-Aware Regularized Decoder

Authors: Ye Huang, Di Kang, Liang Chen, Wenjing Jia, Xiangjian He, Lixin Duan, Xuefei Zhe, Linchao Bao

Abstract: Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-level information to pixel features to boost the pixel representation learning, which cannot fully utilize intra-class and inter-class contextual information. Moreover, these approaches learn soft class centers based on… ▽ More Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-level information to pixel features to boost the pixel representation learning, which cannot fully utilize intra-class and inter-class contextual information. Moreover, these approaches learn soft class centers based on coarse mask prediction, which is prone to error accumulation. To better exploit class level information, we propose a universal Class-Aware Regularization (CAR) approach to optimize the intra-class variance and inter-class distance during feature learning, motivated by the fact that humans can recognize an object by itself no matter which other objects it appears with. Moreover, we design a dedicated decoder for CAR (CARD), which consists of a novel spatial token mixer and an upsampling module, to maximize its gain for existing baselines while being highly efficient in terms of computational cost. Specifically, CAR consists of three novel loss functions. The first loss function encourages more compact class representations within each class, the second directly maximizes the distance between different class centers, and the third further pushes the distance between inter-class centers and pixels. Furthermore, the class center in our approach is directly generated from ground truth instead of from the error-prone coarse prediction. CAR can be directly applied to most existing segmentation models during training, and can largely improve their accuracy at no additional inference overhead. Extensive experiments and ablation studies conducted on multiple benchmark datasets demonstrate that the proposed CAR can boost the accuracy of all baseline models by up to 2.23% mIOU with superior generalization ability. CARD outperforms SOTA approaches on multiple benchmarks with a highly efficient architecture. △ Less

Submitted 10 January, 2023; originally announced January 2023.

Comments: Tech report, text extended from arXiv:2203.07160

NEURAL MARIONETTE: A Transformer-based Multi-action Human Motion Synthesis System

Authors: Weiqiang Wang, Xuefei Zhe, Qiuhong Ke, Di Kang, Tingguang Li, Ruizhi Chen, Linchao Bao

Abstract: We present a neural network-based system for long-term, multi-action human motion synthesis. The system, dubbed as NEURAL MARIONETTE, can produce high-quality and meaningful motions with smooth transitions from simple user input, including a sequence of action tags with expected action duration, and optionally a hand-drawn moving trajectory if the user specifies. The core of our system is a novel… ▽ More We present a neural network-based system for long-term, multi-action human motion synthesis. The system, dubbed as NEURAL MARIONETTE, can produce high-quality and meaningful motions with smooth transitions from simple user input, including a sequence of action tags with expected action duration, and optionally a hand-drawn moving trajectory if the user specifies. The core of our system is a novel Transformer-based motion generation model, namely MARIONET, which can generate diverse motions given action tags. Different from existing motion generation models, MARIONET utilizes contextual information from the past motion clip and future action tag, dedicated to generating actions that can smoothly blend historical and future actions. Specifically, MARIONET first encodes target action tag and contextual information into an action-level latent code. The code is unfolded into frame-level control signals via a time unrolling module, which could be then combined with other frame-level control signals like the target trajectory. Motion frames are then generated in an auto-regressive way. By sequentially applying MARIONET, the system NEURAL MARIONETTE can robustly generate long-term, multi-action motions with the help of two simple schemes, namely "Shadow Start" and "Action Revision". Along with the novel system, we also present a new dataset dedicated to the multi-action motion synthesis task, which contains both action tags and their contextual information. Extensive experiments are conducted to study the action accuracy, naturalism, and transition smoothness of the motions generated by our system. △ Less

Submitted 27 November, 2023; v1 submitted 27 September, 2022; originally announced September 2022.

Learning to Construct 3D Building Wireframes from 3D Line Clouds

Authors: Yicheng Luo, Jing Ren, Xuefei Zhe, Di Kang, Yajing Xu, Peter Wonka, Linchao Bao

Abstract: Line clouds, though under-investigated in the previous work, potentially encode more compact structural information of buildings than point clouds extracted from multi-view images. In this work, we propose the first network to process line clouds for building wireframe abstraction. The network takes a line cloud as input , i.e., a nonstructural and unordered set of 3D line segments extracted from… ▽ More Line clouds, though under-investigated in the previous work, potentially encode more compact structural information of buildings than point clouds extracted from multi-view images. In this work, we propose the first network to process line clouds for building wireframe abstraction. The network takes a line cloud as input , i.e., a nonstructural and unordered set of 3D line segments extracted from multi-view images, and outputs a 3D wireframe of the underlying building, which consists of a sparse set of 3D junctions connected by line segments. We observe that a line patch, i.e., a group of neighboring line segments, encodes sufficient contour information to predict the existence and even the 3D position of a potential junction, as well as the likelihood of connectivity between two query junctions. We therefore introduce a two-layer Line-Patch Transformer to extract junctions and connectivities from sampled line patches to form a 3D building wireframe model. We also introduce a synthetic dataset of multi-view images with ground-truth 3D wireframe. We extensively justify that our reconstructed 3D wireframe models significantly improve upon multiple baseline building reconstruction methods. The code and data can be found at https://github.com/Luo1Cheng/LC2WF. △ Less

Submitted 4 November, 2022; v1 submitted 25 August, 2022; originally announced August 2022.

Comments: 10 pages, 6 figures

Semi-signed prioritized neural fitting for surface reconstruction from unoriented point clouds

Authors: Runsong Zhu, Di Kang, Ka-Hei Hui, Yue Qian, Xuefei Zhe, Zhen Dong, Linchao Bao, Pheng-Ann Heng, Chi-Wing Fu

Abstract: Reconstructing 3D geometry from \emph{unoriented} point clouds can benefit many downstream tasks. Recent shape modeling methods mostly adopt implicit neural representation to fit a signed distance field (SDF) and optimize the network by \emph{unsigned} supervision. However, these methods occasionally have difficulty in finding the coarse shape for complicated objects, especially suffering from the… ▽ More Reconstructing 3D geometry from \emph{unoriented} point clouds can benefit many downstream tasks. Recent shape modeling methods mostly adopt implicit neural representation to fit a signed distance field (SDF) and optimize the network by \emph{unsigned} supervision. However, these methods occasionally have difficulty in finding the coarse shape for complicated objects, especially suffering from the ``ghost'' surfaces (\ie, fake surfaces that should not exist). To guide the network quickly fit the coarse shape, we propose to utilize the signed supervision in regions that are obviously outside the object and can be easily determined, resulting in our semi-signed supervision. To better recover high-fidelity details, a novel importance sampling based on tracked region losses and a progressive positional encoding (PE) prioritize the optimization towards underfitting and complicated regions. Specifically, we voxelize and partition the object space into \emph{sign-known} and \emph{sign-uncertain} regions, in which different supervisions are applied. Besides, we adaptively adjust the sampling rate of each voxel according to the tracked reconstruction loss, so that the network can focus more on the complicated under-fitting regions. To this end, we propose our semi-signed prioritized (SSP) neural fitting, and conduct extensive experiments to demonstrate that SSP achieves state-of-the-art performance on multiple datasets including the ABC subset and various challenging data. The code will be released upon the publication. △ Less

Submitted 14 December, 2022; v1 submitted 14 June, 2022; originally announced June 2022.

Spatial-Temporal Adaptive Graph Convolution with Attention Network for Traffic Forecasting

Authors: Chen Weikang, Li Yawen, Xue Zhe, Li Ang, Wu Guobin

Abstract: Traffic forecasting is one canonical example of spatial-temporal learning task in Intelligent Traffic System. Existing approaches capture spatial dependency with a pre-determined matrix in graph convolution neural operators. However, the explicit graph structure losses some hidden representations of relationships among nodes. Furthermore, traditional graph convolution neural operators cannot aggre… ▽ More Traffic forecasting is one canonical example of spatial-temporal learning task in Intelligent Traffic System. Existing approaches capture spatial dependency with a pre-determined matrix in graph convolution neural operators. However, the explicit graph structure losses some hidden representations of relationships among nodes. Furthermore, traditional graph convolution neural operators cannot aggregate long-range nodes on the graph. To overcome these limits, we propose a novel network, Spatial-Temporal Adaptive graph convolution with Attention Network (STAAN) for traffic forecasting. Firstly, we adopt an adaptive dependency matrix instead of using a pre-defined matrix during GCN processing to infer the inter-dependencies among nodes. Secondly, we integrate PW-attention based on graph attention network which is designed for global dependency, and GCN as spatial block. What's more, a stacked dilated 1D convolution, with efficiency in long-term prediction, is adopted in our temporal block for capturing the different time series. We evaluate our STAAN on two real-world datasets, and experiments validate that our model outperforms state-of-the-art baselines. △ Less

Submitted 7 June, 2022; originally announced June 2022.

WarpingGAN: Warping Multiple Uniform Priors for Adversarial 3D Point Cloud Generation

Authors: Yingzhi Tang, Yue Qian, Qijian Zhang, Yiming Zeng, Junhui Hou, Xuefei Zhe

Abstract: We propose WarpingGAN, an effective and efficient 3D point cloud generation network. Unlike existing methods that generate point clouds by directly learning the mapping functions between latent codes and 3D shapes, Warping-GAN learns a unified local-warping function to warp multiple identical pre-defined priors (i.e., sets of points uniformly distributed on regular 3D grids) into 3D shapes driven… ▽ More We propose WarpingGAN, an effective and efficient 3D point cloud generation network. Unlike existing methods that generate point clouds by directly learning the mapping functions between latent codes and 3D shapes, Warping-GAN learns a unified local-warping function to warp multiple identical pre-defined priors (i.e., sets of points uniformly distributed on regular 3D grids) into 3D shapes driven by local structure-aware semantics. In addition, we also ingeniously utilize the principle of the discriminator and tailor a stitching loss to eliminate the gaps between different partitions of a generated shape corresponding to different priors for boosting quality. Owing to the novel generating mechanism, WarpingGAN, a single lightweight network after one-time training, is capable of efficiently generating uniformly distributed 3D point clouds with various resolutions. Extensive experimental results demonstrate the superiority of our WarpingGAN over state-of-the-art methods in terms of quantitative metrics, visual quality, and efficiency. The source code is publicly available at https://github.com/yztang4/WarpingGAN.git. △ Less

Submitted 24 March, 2022; originally announced March 2022.

Comments: This paper has been accepted by CVPR 2022

REALY: Rethinking the Evaluation of 3D Face Reconstruction

Authors: Zenghao Chai, Haoxian Zhang, Jing Ren, Di Kang, Zhengzhuo Xu, Xuefei Zhe, Chun Yuan, Linchao Bao

Abstract: The evaluation of 3D face reconstruction results typically relies on a rigid shape alignment between the estimated 3D model and the ground-truth scan. We observe that aligning two shapes with different reference points can largely affect the evaluation results. This poses difficulties for precisely diagnosing and improving a 3D face reconstruction method. In this paper, we propose a novel evaluati… ▽ More The evaluation of 3D face reconstruction results typically relies on a rigid shape alignment between the estimated 3D model and the ground-truth scan. We observe that aligning two shapes with different reference points can largely affect the evaluation results. This poses difficulties for precisely diagnosing and improving a 3D face reconstruction method. In this paper, we propose a novel evaluation approach with a new benchmark REALY, consists of 100 globally aligned face scans with accurate facial keypoints, high-quality region masks, and topology-consistent meshes. Our approach performs region-wise shape alignment and leads to more accurate, bidirectional correspondences during computing the shape errors. The fine-grained, region-wise evaluation results provide us detailed understandings about the performance of state-of-the-art 3D face reconstruction methods. For example, our experiments on single-image based reconstruction methods reveal that DECA performs the best on nose regions, while GANFit performs better on cheek regions. Besides, a new and high-quality 3DMM basis, HIFI3D++, is further derived using the same procedure as we construct REALY to align and retopologize several 3D face datasets. We will release REALY, HIFI3D++, and our new evaluation pipeline at https://realy3dface.com. △ Less

Submitted 19 July, 2022; v1 submitted 18 March, 2022; originally announced March 2022.

Comments: Accepted to ECCV 2022, camera-ready version; Project page: https://realy3dface.com; Code: https://github.com/czh-98/REALY

CAR: Class-aware Regularizations for Semantic Segmentation

Authors: Ye Huang, Di Kang, Liang Chen, Xuefei Zhe, Wenjing Jia, Xiangjian He, Linchao Bao

Abstract: Recent segmentation methods, such as OCR and CPNet, utilizing "class level" information in addition to pixel features, have achieved notable success for boosting the accuracy of existing network modules. However, the extracted class-level information was simply concatenated to pixel features, without explicitly being exploited for better pixel representation learning. Moreover, these approaches le… ▽ More Recent segmentation methods, such as OCR and CPNet, utilizing "class level" information in addition to pixel features, have achieved notable success for boosting the accuracy of existing network modules. However, the extracted class-level information was simply concatenated to pixel features, without explicitly being exploited for better pixel representation learning. Moreover, these approaches learn soft class centers based on coarse mask prediction, which is prone to error accumulation. In this paper, aiming to use class level information more effectively, we propose a universal Class-Aware Regularization (CAR) approach to optimize the intra-class variance and inter-class distance during feature learning, motivated by the fact that humans can recognize an object by itself no matter which other objects it appears with. Three novel loss functions are proposed. The first loss function encourages more compact class representations within each class, the second directly maximizes the distance between different class centers, and the third further pushes the distance between inter-class centers and pixels. Furthermore, the class center in our approach is directly generated from ground truth instead of from the error-prone coarse prediction. Our method can be easily applied to most existing segmentation models during training, including OCR and CPNet, and can largely improve their accuracy at no additional inference overhead. Extensive experiments and ablation studies conducted on multiple benchmark datasets demonstrate that the proposed CAR can boost the accuracy of all baseline models by up to 2.23% mIOU with superior generalization ability. The complete code is available at https://github.com/edwardyehuang/CAR. △ Less

Submitted 14 July, 2022; v1 submitted 14 March, 2022; originally announced March 2022.

Comments: ECCV 2022 camera ready. Codes and models are available at https://github.com/edwardyehuang/CAR

Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders

Authors: Jing Li, Di Kang, Wenjie Pei, Xuefei Zhe, Ying Zhang, Zhenyu He, Linchao Bao

Abstract: Generating conversational gestures from speech audio is challenging due to the inherent one-to-many mapping between audio and body motions. Conventional CNNs/RNNs assume one-to-one mapping, and thus tend to predict the average of all possible target motions, resulting in plain/boring motions during inference. In order to overcome this problem, we propose a novel conditional variational autoencoder… ▽ More Generating conversational gestures from speech audio is challenging due to the inherent one-to-many mapping between audio and body motions. Conventional CNNs/RNNs assume one-to-one mapping, and thus tend to predict the average of all possible target motions, resulting in plain/boring motions during inference. In order to overcome this problem, we propose a novel conditional variational autoencoder (VAE) that explicitly models one-to-many audio-to-motion mapping by splitting the cross-modal latent code into shared code and motion-specific code. The shared code mainly models the strong correlation between audio and motion (such as the synchronized audio and motion beats), while the motion-specific code captures diverse motion information independent of the audio. However, splitting the latent code into two parts poses training difficulties for the VAE model. A mapping network facilitating random sampling along with other techniques including relaxed motion loss, bicycle constraint, and diversity loss are designed to better train the VAE. Experiments on both 3D and 2D motion datasets verify that our method generates more realistic and diverse motions than state-of-the-art methods, quantitatively and qualitatively. Finally, we demonstrate that our method can be readily used to generate motion sequences with user-specified motion clips on the timeline. Code and more results are at https://jingli513.github.io/audio2gestures. △ Less

Submitted 15 August, 2021; originally announced August 2021.

Orthonormal Product Quantization Network for Scalable Face Image Retrieval

Authors: Ming Zhang, Xuefei Zhe, Hong Yan

Abstract: Existing deep quantization methods provided an efficient solution for large-scale image retrieval. However, the significant intra-class variations like pose, illumination, and expressions in face images, still pose a challenge for face image retrieval. In light of this, face image retrieval requires sufficiently powerful learning metrics, which are absent in current deep quantization works. Moreov… ▽ More Existing deep quantization methods provided an efficient solution for large-scale image retrieval. However, the significant intra-class variations like pose, illumination, and expressions in face images, still pose a challenge for face image retrieval. In light of this, face image retrieval requires sufficiently powerful learning metrics, which are absent in current deep quantization works. Moreover, to tackle the growing unseen identities in the query stage, face image retrieval drives more demands regarding model generalization and system scalability than general image retrieval tasks. This paper integrates product quantization with orthonormal constraints into an end-to-end deep learning framework to effectively retrieve face images. Specifically, a novel scheme that uses predefined orthonormal vectors as codewords is proposed to enhance the quantization informativeness and reduce codewords' redundancy. A tailored loss function maximizes discriminability among identities in each quantization subspace for both the quantized and original features. An entropy-based regularization term is imposed to reduce the quantization error. Experiments are conducted on four commonly-used face datasets under both seen and unseen identities retrieval settings. Our method outperforms all the compared deep hashing/quantization state-of-the-arts under both settings. Results validate the effectiveness of the proposed orthonormal codewords in improving models' standard retrieval performance and generalization ability. Combing with further experiments on two general image datasets, it demonstrates the broad superiority of our method for scalable image retrieval. △ Less

Submitted 12 May, 2023; v1 submitted 1 July, 2021; originally announced July 2021.

Comments: Published in Pattern Recognition, supplementary material can be found in Github project page

Animatable Neural Radiance Fields from Monocular RGB Videos

Authors: Jianchuan Chen, Ying Zhang, Di Kang, Xuefei Zhe, Linchao Bao, Xu Jia, Huchuan Lu

Abstract: We present animatable neural radiance fields (animatable NeRF) for detailed human avatar creation from monocular videos. Our approach extends neural radiance fields (NeRF) to the dynamic scenes with human movements via introducing explicit pose-guided deformation while learning the scene representation network. In particular, we estimate the human pose for each frame and learn a constant canonical… ▽ More We present animatable neural radiance fields (animatable NeRF) for detailed human avatar creation from monocular videos. Our approach extends neural radiance fields (NeRF) to the dynamic scenes with human movements via introducing explicit pose-guided deformation while learning the scene representation network. In particular, we estimate the human pose for each frame and learn a constant canonical space for the detailed human template, which enables natural shape deformation from the observation space to the canonical space under the explicit control of the pose parameters. To compensate for inaccurate pose estimation, we introduce the pose refinement strategy that updates the initial pose during the learning process, which not only helps to learn more accurate human reconstruction but also accelerates the convergence. In experiments we show that the proposed approach achieves 1) implicit human geometry and appearance reconstruction with high-quality details, 2) photo-realistic rendering of the human from novel views, and 3) animation of the human with novel poses. △ Less

Submitted 7 September, 2021; v1 submitted 25 June, 2021; originally announced June 2021.

Comments: 12 pages, 12 figures

Model-based 3D Hand Reconstruction via Self-Supervised Learning

Authors: Yujin Chen, Zhigang Tu, Di Kang, Linchao Bao, Ying Zhang, Xuefei Zhe, Ruizhi Chen, Junsong Yuan

Abstract: Reconstructing a 3D hand from a single-view RGB image is challenging due to various hand configurations and depth ambiguity. To reliably reconstruct a 3D hand from a monocular image, most state-of-the-art methods heavily rely on 3D annotations at the training stage, but obtaining 3D annotations is expensive. To alleviate reliance on labeled training data, we propose S2HAND, a self-supervised 3D ha… ▽ More Reconstructing a 3D hand from a single-view RGB image is challenging due to various hand configurations and depth ambiguity. To reliably reconstruct a 3D hand from a monocular image, most state-of-the-art methods heavily rely on 3D annotations at the training stage, but obtaining 3D annotations is expensive. To alleviate reliance on labeled training data, we propose S2HAND, a self-supervised 3D hand reconstruction network that can jointly estimate pose, shape, texture, and the camera viewpoint. Specifically, we obtain geometric cues from the input image through easily accessible 2D detected keypoints. To learn an accurate hand reconstruction model from these noisy geometric cues, we utilize the consistency between 2D and 3D representations and propose a set of novel losses to rationalize outputs of the neural network. For the first time, we demonstrate the feasibility of training an accurate 3D hand reconstruction network without relying on manual annotations. Our experiments show that the proposed method achieves comparable performance with recent fully-supervised methods while using fewer supervision data. △ Less

Submitted 22 March, 2021; originally announced March 2021.

Comments: Accepted by CVPR21

High-Fidelity 3D Digital Human Head Creation from RGB-D Selfies

Authors: Linchao Bao, Xiangkai Lin, Yajing Chen, Haoxian Zhang, Sheng Wang, Xuefei Zhe, Di Kang, Haozhi Huang, Xinwei Jiang, Jue Wang, Dong Yu, Zhengyou Zhang

Abstract: We present a fully automatic system that can produce high-fidelity, photo-realistic 3D digital human heads with a consumer RGB-D selfie camera. The system only needs the user to take a short selfie RGB-D video while rotating his/her head, and can produce a high quality head reconstruction in less than 30 seconds. Our main contribution is a new facial geometry modeling and reflectance synthesis pro… ▽ More We present a fully automatic system that can produce high-fidelity, photo-realistic 3D digital human heads with a consumer RGB-D selfie camera. The system only needs the user to take a short selfie RGB-D video while rotating his/her head, and can produce a high quality head reconstruction in less than 30 seconds. Our main contribution is a new facial geometry modeling and reflectance synthesis procedure that significantly improves the state-of-the-art. Specifically, given the input video a two-stage frame selection procedure is first employed to select a few high-quality frames for reconstruction. Then a differentiable renderer based 3D Morphable Model (3DMM) fitting algorithm is applied to recover facial geometries from multiview RGB-D data, which takes advantages of a powerful 3DMM basis constructed with extensive data generation and perturbation. Our 3DMM has much larger expressive capacities than conventional 3DMM, allowing us to recover more accurate facial geometry using merely linear basis. For reflectance synthesis, we present a hybrid approach that combines parametric fitting and CNNs to synthesize high-resolution albedo/normal maps with realistic hair/pore/wrinkle details. Results show that our system can produce faithful 3D digital human faces with extremely realistic details. The main code and the newly constructed 3DMM basis is publicly available. △ Less

Submitted 29 June, 2021; v1 submitted 12 October, 2020; originally announced October 2020.

Comments: Code: https://github.com/tencent-ailab/hifi3dface

Semantic Hierarchy Preserving Deep Hashing for Large-scale Image Retrieval

Authors: Ming Zhang, Xuefei Zhe, Le Ou-Yang, Shifeng Chen, Hong Yan

Abstract: Deep hashing models have been proposed as an efficient method for large-scale similarity search. However, most existing deep hashing methods only utilize fine-level labels for training while ignoring the natural semantic hierarchy structure. This paper presents an effective method that preserves the classwise similarity of full-level semantic hierarchy for large-scale image retrieval. Experiments… ▽ More Deep hashing models have been proposed as an efficient method for large-scale similarity search. However, most existing deep hashing methods only utilize fine-level labels for training while ignoring the natural semantic hierarchy structure. This paper presents an effective method that preserves the classwise similarity of full-level semantic hierarchy for large-scale image retrieval. Experiments on two benchmark datasets show that our method helps improve the fine-level retrieval performance. Moreover, with the help of the semantic hierarchy, it can produce significantly better binary codes for hierarchical retrieval, which indicates its potential of providing more user-desired retrieval results. △ Less

Submitted 22 June, 2021; v1 submitted 31 January, 2019; originally announced January 2019.

Deep Class-Wise Hashing: Semantics-Preserving Hashing via Class-wise Loss

Authors: Xuefei Zhe, Shifeng Chen, Hong Yan

Abstract: Deep supervised hashing has emerged as an influential solution to large-scale semantic image retrieval problems in computer vision. In the light of recent progress, convolutional neural network based hashing methods typically seek pair-wise or triplet labels to conduct the similarity preserving learning. However, complex semantic concepts of visual contents are hard to capture by similar/dissimila… ▽ More Deep supervised hashing has emerged as an influential solution to large-scale semantic image retrieval problems in computer vision. In the light of recent progress, convolutional neural network based hashing methods typically seek pair-wise or triplet labels to conduct the similarity preserving learning. However, complex semantic concepts of visual contents are hard to capture by similar/dissimilar labels, which limits the retrieval performance. Generally, pair-wise or triplet losses not only suffer from expensive training costs but also lack in extracting sufficient semantic information. In this regard, we propose a novel deep supervised hashing model to learn more compact class-level similarity preserving binary codes. Our deep learning based model is motivated by deep metric learning that directly takes semantic labels as supervised information in training and generates corresponding discriminant hashing code. Specifically, a novel cubic constraint loss function based on Gaussian distribution is proposed, which preserves semantic variations while penalizes the overlap part of different classes in the embedding space. To address the discrete optimization problem introduced by binary codes, a two-step optimization strategy is proposed to provide efficient training and avoid the problem of gradient vanishing. Extensive experiments on four large-scale benchmark databases show that our model can achieve the state-of-the-art retrieval performance. Moreover, when training samples are limited, our method surpasses other supervised deep hashing methods with non-negligible margins. △ Less

Submitted 12 March, 2018; originally announced March 2018.

Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval

Authors: Xuefei Zhe, Shifeng Chen, Hong Yan

Abstract: Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in the embedding space has been used to improve the performance of several DDML methods. However, the commonly used Euclidean distance is no longer an accurate met… ▽ More Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in the embedding space has been used to improve the performance of several DDML methods. However, the commonly used Euclidean distance is no longer an accurate metric for $L2$-normalized embedding space, i.e., a hyper-sphere. Another challenge of current DDML methods is that their loss functions are usually based on rigid data formats, such as the triplet tuple. Thus, an extra process is needed to prepare data in specific formats. In addition, their losses are obtained from a limited number of samples, which leads to a lack of the global view of the embedding space. In this paper, we replace the Euclidean distance with the cosine similarity to better utilize the $L2$-normalization, which is able to attenuate the curse of dimensionality. More specifically, a novel loss function based on the von Mises-Fisher distribution is proposed to learn a compact hyper-spherical embedding space. Moreover, a new efficient learning algorithm is developed to better capture the global structure of the embedding space. Experiments for both classification and retrieval tasks on several standard datasets show that our method achieves state-of-the-art performance with a simpler training procedure. Furthermore, we demonstrate that, even with a small number of convolutional layers, our model can still obtain significantly better classification performance than the widely used softmax loss. △ Less

Submitted 27 March, 2018; v1 submitted 26 February, 2018; originally announced February 2018.

Comments: codes will come soon