Absolute Coordinates Make Motion Generation Easy

TL;DR

This paper demonstrates that using absolute joint coordinates in global space for text-to-motion generation improves fidelity, scalability, and downstream task support compared to traditional relative representations, simplifying the process.

Contribution

The authors propose a simple, absolute coordinate-based motion representation that outperforms relative methods, enabling better motion quality and easier downstream task integration.

Findings

Higher motion fidelity with absolute coordinates

Improved text alignment and scalability

Supports downstream tasks without additional reengineering

Abstract

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.