OpenT2M is a massive open-source motion dataset (2,800+ hours) that addresses the data starvation in text-to-motion generation.
March 20, 2026
Original Paper
OpenT2M: No-frill Motion Generation with Open-source,Large-scale, High-quality Data
arXiv · 2603.18623
The Takeaway
Existing motion datasets were too small for robust generalization; this release is a 'million-level' dataset with physical feasibility validation. It provides the scale necessary to bring motion generation closer to the success seen in text and image domains.
From the abstract
Text-to-motion (T2M) generation aims to create realistic human movements from text descriptions, with promising applications in animation and robotics. Despite recent progress, current T2M models perform poorly on unseen text descriptions due to the small scale and limited diversity of existing motion datasets. To address this problem, we introduce OpenT2M, a million-level, high-quality, and open-source motion dataset containing over 2800 hours of human motion. Each sequence undergoes rigorous q