A curated, public list of resources for biomechanics and human motion analysis: datasets, processing tools, software for simulation, educational videos, lectures, etc.

[RSS 2024]: Expressive Whole-Body Control for Humanoid Robots

🏃‍♀️ A curated list about human motion capture, analysis and synthesis.

Official PyTorch implementation of the paper "TEMOS: Generating diverse human motions from textual descriptions", ECCV 2022 (Oral)

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

An aggregation of human motion understanding research.

[CVPR 2024] Official Implementation of "Seamless Human Motion Composition with Blended Positional Encodings".

[NeurIPS 2023] InsActor: Instruction-driven Physics-based Characters

Official implementation of TRACE, the TRAjectory Diffusion Model for Controllable PEdestrians, from the CVPR 2023 paper: "Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion".

Forecasting Characteristic 3D Poses of Human Actions (CVPR'22) 🏃‍♂️

PyTorch implementation of our graph convolutional network (GCN) for human motion generation from music. Also with paired dance-music data for training!

Official implementation of TeSMo, a method for text-controlled scene-aware motion generation, from the ECCV 2024 paper: "Generating Human Interaction Motions in Scenes with Text Control".

Text-driven human motion generation surveys, datasets and models.

[ECCV 2022] SAGA: Stochastic Whole-Body Grasping with Contact

[CVPRW 2024] Official Implementation of "in2IN: Leveraging individual Information to Generate Human INteractions".

✨ [CVPR 2023] NeuralPCI: Spatio-temporal Neural Field for 3D Point Cloud Multi-frame Non-linear Interpolation

Implementation of Constructing Human Motion Manifold with Sequential Networks in PyTorch

Official code of [AAAI2024] Expressive Forecasting of 3D Whole-body Human Motions

Code for the ECCV'22 paper "Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos".

Code and dataset of human retargeting approach to transfer motion and appearance between monocular videos. Check the examples from our dataset with several paired actors and motions!

Deep Learning for Skeleton Based Human Motion Rehabilitation Assessment: A Benchmark

Evaluating Human Motion Generation Models

Dual-phase generative model for creating realistic stick figure animations from text prompts.

Human motion trajectory based on the minimum jerk principle and OpenSim model for the human upper limb

Indoor radio based ray-tracing with human blockage.

A Supervised VAE Based Gen Model for Human Motion

Convert AMASS-format 3D joint sequences to SMPL meshes. via optimization. For Human Motion Prediction.

CHAIR: 3D Human-Interaction Dataset. Human Object Interaction (HOI) dataset, focusing on interactions between humans and chairs.

Human motion dataset for assembly tasks

Repository using Transfer learning of Yolov8n-pose to obtain key points in pose estimation and time series generation for each video frame