A real-time system that simultaneously captures human pose, reconstructs the scene in sparse 3D points, and localizes the human in the scene with 6 IMUs and a body-worn phone camera

A real-time human motion capture system based on 6 IMUs, upgrading PIP through the incorporation of non-inertial forces

3D-space human motion capture from 6 IMUs built upon TransPose, PIP, and PNP

Momentum Human Rig is an anatomically-inspired parametric full-body digital human model developed at Meta. It includes: A parametric body skeletal model; A realistic 3D mesh skinned to the skeleton…

Uncertainty-driven Human Motion Estimation from IMU and UWB

Nymeria: a massive collection of multimodal egocentric daily motion in the wild

DeepPrivacy: A Generative Adversarial Network for Face Anonymization

Official Code for ICCV 2021 paper "Towards Flexible Blind JPEG Artifacts Removal (FBCNN)"

Restore Anything Pipeline (RAP): Segment Anything Meets Image Restoration

Official Code for ECCV 2024 paper "EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere"

Isaac Gym Reinforcement Learning Environments

CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control

Official Implementation of the ICCV 2023 paper: Perpetual Humanoid Control for Real-time Simulated Avatars

[ICCV, 2023] Multiple humans in 3D captured by dynamic and static cameras in 4K.

VPoser: Variational Human Pose Prior

[ ECCV 2024 ] MotionLCM: This repo is the official implementation of "MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model"

Structured state space sequence models

Code for Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors

Python module for parsing BVH (Biovision hierarchical data) mocap files

Python implementation accompanying the Transformer Inertial Poser paper at SIGGRAPH Asia 2022

Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time

A real-time system that captures physically correct human motion, joint torques, and ground reaction forces with only 6 inertial measurement units

Official Code for ACM SIGGRAPH 2024 paper "Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Ranging"

CVPR 2022 - Official code repository for the paper: Accurate 3D Body Shape Regression using Metric and Semantic Attributes.

[NeurIPS 2023] Official implementation of the paper "Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset"

SMPL/SMPL-H version of HumanML3D

Official Code for ECCV 2022 paper "AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing"

Data preparation and loader for AMASS

(CVPR 2023) Pytorch implementation of “T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations”