A library for machine learning research on motion capture data

Official Pytorch implementation for 2021 ICCV paper "Learning Motion Priors for 4D Human Body Capture in 3D Scenes" and trained models / data

Python parser for URDFs

Read You Like a "Mesh":Interactive Body Capture in First Person Video

Implementation for the paper: Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images (3DV 2021 oral)

Official code and data for EgoBody dataset (2022 ECCV)

Solving Optical MoCap Automatically

iMapper: Interaction-guided Scene Mapping from Monocular Videos

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video ta…

Penn Action Dataset, with human body joints for all frames!

A technical report on convolution arithmetic in the context of deep learning

A simple armature retargeting tool for Blender

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

End-to-End Object Detection with Transformers

Code repository for the paper "Tracking People with 3D Representations". NeurIPS 2021

Google Drive Public File Downloader when Curl/Wget Fails

Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering

ICCV19: Official code of Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation

Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]