Stars
[CVPR 2023] H2ONet: Hand-Occlusion-and-Orientation-aware Network for Real-time 3D Hand Mesh Reconstruction, Pytorch implementation.
[cvpr19] Code to generate images from the ObMan dataset, synthetic renderings of hands holding objects (or hands in isolation)
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
End-to-end Recovery of Human Shape and Pose with tensorflow 2.0
Code release for Image Sculpting: Precise Object Editing with 3D Geometry Control [CVPR 2024]
GenZI: Zero-Shot 3D Human-Scene Interaction Generation (CVPR 2024)
Count the MACs / FLOPs of your PyTorch model.
Nightly release of ControlNet 1.1
High-Resolution Image Synthesis with Latent Diffusion Models
PyTorch reimplementation of minimal-hand (CVPR2020)
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Official code for "SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation"
The official PyTorch code for RoHM: Robust Human Motion Reconstruction via Diffusion.
Project page for End-to-end Recovery of Human Shape and Pose
[CVPR 2022 Oral] Official PyTorch Implementation of "GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras”.
A repository and benchmark for online test-time adaptation.
[ICCV 2023] This repo is official PyTorch implementation of Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction.
Code for <Domain Adaptive Video Segmentation via Temporal Consistency Regularization> in ICCV 2021
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"
Official implementation of CVPR2022 paper "Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video"
Fork of the GEM project (https://github.com/facebookresearch/GradientEpisodicMemory) including Meta-Experience Replay (MER) methods from the ICLR 2019 paper (https://openreview.net/pdf?id=B1gTShAct7)
C3DPO - Canonical 3D Pose Networks for Non-rigid Structure From Motion.
Self-Supervised Learning for Domain Adaptation on Point-Clouds
Reproduction of the CVPR 2020 paper - Self-supervised monocular trained depth estimation using self-attention and discrete disparity volume
[TCSVT 2023] Self-Supervised Monocular Depth Estimation with Self-Reference Distillation and Disparity Offset Refinement
[CVPR 2023] Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation