motion-synthesis

Official implementation of "MoMask: Generative Masked Modeling of 3D Human Motions (CVPR2024)"

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

This is a repository for GraspXL, which can generate objective-drive grasping motions for 500k+ objects with different dexterous hands.

An aggregation of human motion understanding research.

Official implementations for "Action2Motion: Conditioned Generation of 3D Human Motions (ACM MultiMedia 2020)"

Interactive Character Control with Auto-Regressive Motion Diffusion Models

[NeurIPS 2020] Official PyTorch Implementation of "Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis". NeurIPS 2020.

[SIGGRAPH 2022] ARTEMIS, a novel neural modeling and rendering pipeline for generating ARTiculated neural pets with appEarance and Motion synthesIS.

Motion Puzzle - Official PyTorch implementation

Official repository for "MMM: Generative Masked Motion Model" (CVPR 2024 -- Highlight)

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

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

[CVPR 2025] InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation

[ECCV 2024] Official PyTorch implement of paper "ParCo: Part-Coordinating Text-to-Motion Synthesis": http://arxiv.org/abs/2403.18512

Official repository for "BAMM: Bidirectional Autoregressive Motion Model (ECCV 2024)"

Official dataset and code for "ELMO: Enhanced Real-time LiDAR Motion Capture through Upsampling" and "MOVIN: Real-time Motion Capture using a Single LiDAR"

Official implementation of "Diverse Motion Stylization for Multiple Style Domains via Spatial-Temporal Graph-Based Generative Model"

Implementation of Constructing Human Motion Manifold with Sequential Networks in PyTorch

This is the implementation of CVPR 2025 paper "BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects". The authors include: Wanyue Zhang, Rishabh Dabral, Vladislav Golyanik, Vasileios Choutas, Eduardo Alvarado, Thabo Beeler, Marc Habermann, Christian Theobalt

Official implementation for "MOCHA: Real-Time Motion Characterization via Context Matching" [SIGGRAPH Asia 2023]