This repository contains the source code, models and data files for the work titled: "Unsupervised Image Style Embeddings for Retrieval and Recognition Tasks". This was accepted at WACV 2020. The source code files, model checkpoints and data will be made available after the conference.
Official PyTorch implementation of "CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding" (WACV 2026). CAPE resolves referential ambiguity in cluttered scenes by fusing complementary pointing heatmaps with CLIP semantic guidance.
[WACV 2026] PyTorch code for 4D-Animal: Freely Reconstructing Animatable 3D Animals from Videos
[WACV 2024] Separable Self and Mixed Attention Transformers for Efficient Object Tracking
NITEC: Versatile Hand-Annotated Eye Contact Dataset for Ego-Vision Interaction (WACV24)
The project is the official implementation of our WACV 2023 paper, "Real-Time Restoration of Dark Stereo Images"
[WACV, 2026] Official implementation of "A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis"
This repository collects the list of accepted paper from (currently only deep learning) top conferences. All lists are crawled by python scripts for later maintenance and analysis.
[WACV 2026] Revisiting Retentive Networks for Fast Range-View 3D LiDAR Semantic Segmentation
Cross-task Attention Mechanism for Dense Multi-task Learning (WACV 2023)
Combined Physics and Event Camera Simulator for Slip Detection (WACV-W 2025)
Command-line Paper Downloader for arxiv.org, NeurIPS, ICLR, CVPR, ICCV, WACV & ECCV
Official implementation of "Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis"(WACV 2022/CVPRW 2021)
[WACV 2026]Official Code of the paper “Equivariant Sampling for Improving Diffusion Model-based Image Restoration“
[WACV 2026] Code for "Towards Fast and Scalable Normal Integration using Continuous Components"
[WACV2025] source code of StrDA: https://arxiv.org/abs/2410.09913
Video Question Answering | Video QA | VQA
[WACV2025 Oral] SUM: Saliency Unification through Mamba for Visual Attention Modeling
Official and maintained implementation of the paper "Differentiable JPEG: The Devil is in the Details" (WACV 2024)
Add a description, image, and links to the wacv topic page so that developers can more easily learn about it.
To associate your repository with the wacv topic, visit your repo's landing page and select "manage topics."