[CVPR 2022] "Mining Multi-View Information: A Strong Self-Supervised Framework for Depth-based 3D Hand Pose and Mesh Estimation"

workshop, tutorial, oral, and poster with notes in cvpr2022

[CVPR 2022] Official implemention of the paper "LAR-SR: A Local Autoregressive Model for Image Super-Resolution“

Official repository of our submission "Adversarial Robustness through the Lens of Convolutional Filters" for the CVPR2022 Workshop "The Art of Robustness: Devil and Angel in Adversarial Machine Learning Workshop"

Official PyTorch implementation of CVPRW 2022 paper "Attention Consistency on Visual Corruptions for Single-Source Domain Generalization"

RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes, CVPR 2022

SPAMs: Structured Implicit Parametric Models [CVPR 22]

PyTorch Implementation of Stereoscopic Universal Perturbations across Different Architectures and Datasets (CVPR 2022)

Code accompanying CVPR 2022 paper, " SOMSI: Spherical Novel View Synthesis with Soft Occlusion Multi-Sphere Images"

Dynamic Task Expansion with Continual Transformers, accepted at CVPR 2022

Official PyTorch Implementation for CVPR2022 paper "Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection"

A forked repo from Torch-Points3D for VoteNet with the Fast Point Transformer backbone.

[CVPR 2022] Inertia-Guided Flow Completion and Style Fusion for Video Inpainting

[CVPR22] Official codebase of Semantic Segmentation by Early Region Proxy.

Official Source Code of the paper "Exploring Effective Data for Surrogate Training Towards Black-box Attack", which is accepted by CVPR 2022

Paper Statistics for CVPR‘22

Non-linear Motion Estimation for Video Frame Interpolation using Space-time Convolutions

Code for "Style-Structure Disentangled Features and Normalizing Flows for Diverse Icon Colorization", CVPR 2022.

Pytorch Implementation of Task Adaptive Parameter Sharing for Multi-Task Learning (CVPR 2022)

Video-Text Representation Learning via Differentiable Weak Temporal Alignment (CVPR 2022)