English

Embracing Aleatoric Uncertainty: Generating Diverse 3D Human Motion

Computer Vision and Pattern Recognition 2025-08-29 v1

Abstract

Generating 3D human motions from text is a challenging yet valuable task. The key aspects of this task are ensuring text-motion consistency and achieving generation diversity. Although recent advancements have enabled the generation of precise and high-quality human motions from text, achieving diversity in the generated motions remains a significant challenge. In this paper, we aim to overcome the above challenge by designing a simple yet effective text-to-motion generation method, \textit{i.e.}, Diverse-T2M. Our method introduces uncertainty into the generation process, enabling the generation of highly diverse motions while preserving the semantic consistency of the text. Specifically, we propose a novel perspective that utilizes noise signals as carriers of diversity information in transformer-based methods, facilitating a explicit modeling of uncertainty. Moreover, we construct a latent space where text is projected into a continuous representation, instead of a rigid one-to-one mapping, and integrate a latent space sampler to introduce stochastic sampling into the generation process, thereby enhancing the diversity and uncertainty of the outputs. Our results on text-to-motion generation benchmark datasets~(HumanML3D and KIT-ML) demonstrate that our method significantly enhances diversity while maintaining state-of-the-art performance in text consistency.

Keywords

Cite

@article{arxiv.2508.20604,
  title  = {Embracing Aleatoric Uncertainty: Generating Diverse 3D Human Motion},
  author = {Zheng Qin and Yabing Wang and Minghui Yang and Sanping Zhou and Ming Yang and Le Wang},
  journal= {arXiv preprint arXiv:2508.20604},
  year   = {2025}
}
R2 v1 2026-07-01T05:09:55.555Z