An aggregation of human motion understanding research.

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

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

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

A Supervised VAE Based Gen Model for Human Motion

Evaluating Human Motion Generation Models

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

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

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".

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".

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

Indoor radio based ray-tracing with human blockage.

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

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

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

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

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

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

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

This repository contains two Gazebo plugins for simulation crowd motion: one is the classical Social Force Model and the other is the Headed Social Force Model, where also the orientation of each pedestrian is taken into account.