{"ID":2877100,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.20604","arxiv_id":"2508.20604","title":"Embracing Aleatoric Uncertainty: Generating Diverse 3D Human Motion","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.","short_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 generat...","url_abs":"https://arxiv.org/abs/2508.20604","url_pdf":"https://arxiv.org/pdf/2508.20604v1","authors":"[\"Zheng Qin\",\"Yabing Wang\",\"Minghui Yang\",\"Sanping Zhou\",\"Ming Yang\",\"Le Wang\"]","published":"2025-08-28T09:49:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}