State-of-the-art text-to-motion generation models rely on the kinematic-aware, local-relative motion representation popularized by HumanML3D, which encodes motion relative to the pelvis and to the previous frame with built-in redundancy. While this design simplifies training for earlier generation models, it introduces critical limitations for diffusion models and hinders applicability to downstream tasks. In this work, we revisit the motion representation and propose a radically simplified and long-abandoned alternative for text-to-motion generation: absolute joint coordinates in global space. Through systematic analysis of design choices, we show that this formulation achieves significantly higher motion fidelity, improved text alignment, and strong scalability, even with a simple Transformer backbone and no auxiliary kinematic-aware losses. Moreover, our formulation naturally supports downstream tasks such as text-driven motion control and temporal/spatial editing without additional task-specific reengineering and costly classifier guidance generation from control signals. Finally, we demonstrate promising generalization to directly generate SMPL-H mesh vertices in motion from text, laying a strong foundation for future research and motion-related applications.
man steps to the right steps in a small counterclockwise circle, throws right arm then steps in a larger backward counterclockwise circle.
A person stands on one legs in yoga pose.
A person climbs a ladder.
Person turns to left, takes three steps forward, sits down, and then walks back to starting place.
A person walks forward, stepping up with their right leg and down with their left, then turns to their left and walks, then turns to their left and starts stepping up.
@article{meng2025absolute,
title={Absolute Coordinates Make Motion Generation Easy},
author={Meng, Zichong and Han, Zeyu and Peng, Xiaogang and Xie, Yiming and Jiang, Huaizu},
journal={arXiv preprint arXiv:2505.19377},
year={2025}
}