← Back to Benchmarks
simmediumvision-robotmetric · varies

OpenT2M: No-frill Motion Generation with Open-source,Large-scale, High-quality Data

Description

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

Source

http://arxiv.org/abs/2603.18623v1