AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
Conditional human motion generation remains a fundamental challenge in computer vision and robotics. Despite significant progress, current methods are often constrained by fixed modality configurations and task-specific architectures, leaving cross-modal interactions and the scaling laws of multimodal-conditioned synthesis largely underexplored. A key bottleneck is the scarcity of large-scale modality-aligned motion data, limiting generalization across diverse control signals. In this work, we introduce OmniHuMo, a large-scale, high-quality dataset comprising over 5,000 hours of motion and 3.2 million sequences with precisely aligned multimodal annotations (e.g., text, speech, music, and ...
| Authors | Yiheng Li, Zhuo Li, Ruibing Hou et al. |
|---|---|
| Primary category | cs.CV |
| Published | 28 May 2026 |
| Last updated at source | 31 May 2026 |
Popularity, last 3 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- L-yiheng/OmniHuMoDataset · cited by
Models and datasets referencing this paper
- L-yiheng/OmniHuMoDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 19 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.