Code repository for the paper "Tracking People by Predicting 3D Appearance, Location & Pose". (CVPR 2022 Oral)

A PyTorch Implementation of MANO hand model.

A library for differentiable nonlinear optimization

Stochastic Scene-Aware Motion Prediction https://samp.is.tue.mpg.de/

Code for ICCV2021 paper SPEC: Seeing People in the Wild with an Estimated Camera

Estimating expressive body with detailed face and hand articulation from a single image

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

Code for the paper: Evolving objective function for improved variational quantum optimization.

This repository contains the code for the paper "SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks"

[CVPR 2021 Oral] Reconstructing 3D Human Pose by Watching Humans in the Mirror

A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

Project website for 3D Bird Reconstruction (ECCV 2020)

Official PyTorch implementation of "I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image", ECCV 2020

GRAB: A Dataset of Whole-Body Human Grasping of Objects

GrabNet: A Generative model to generate realistic 3D hands grasping unseen objects (ECCV2020)

ExPose - EXpressive POse and Shape rEgression

ECCV2020 - Official code repository for the paper : STAR - A Sparse Trained Articulated Human Body Regressor

Normalizing flows in PyTorch

Pytorch implementation of SIREN - Implicit Neural Representations with Periodic Activation Function

Code + Data for CVPR 2020 oral paper "Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Data."

Code for "Deep Snake for Real-Time Instance Segmentation" CVPR 2020 oral

Code repository for the paper: "Coherent Reconstruction of Multiple Humans from a Single Image" in CVPR'20

C++ implementation for computing occupancy grids and signed distance functions (SDFs) from watertight meshes.

High-Resolution 3D Human Digitization from A Single Image.

[cvpr 20] Demo, training and evaluation code for joint hand-object pose estimation in sparsely annotated videos

Holopix50k: A Large-Scale In-the-wild Stereo Image Dataset

Code for "Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image", CVPR 2020

Project for paper "Learning 3D Human Dynamics from Video"

Reactive Navigation with Semantic Feedback Using ROS