Kimodo: Scaling Controllable Human Motion Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908889938657280 |
|---|---|
| author | Rempe, Davis Petrovich, Mathis Yuan, Ye Zhang, Haotian Peng, Xue Bin Jiang, Yifeng Wang, Tingwu Iqbal, Umar Minor, David de Ruyter, Michael Li, Jiefeng Tessler, Chen Lim, Edy Jeong, Eugene Wu, Sam Hassani, Ehsan Huang, Michael Yu, Jin-Bey Chung, Chaeyeon Song, Lina Dionne, Olivier Kautz, Jan Yuen, Simon Fidler, Sanja |
| author_facet | Rempe, Davis Petrovich, Mathis Yuan, Ye Zhang, Haotian Peng, Xue Bin Jiang, Yifeng Wang, Tingwu Iqbal, Umar Minor, David de Ruyter, Michael Li, Jiefeng Tessler, Chen Lim, Edy Jeong, Eugene Wu, Sam Hassani, Ehsan Huang, Michael Yu, Jin-Bey Chung, Chaeyeon Song, Lina Dionne, Olivier Kautz, Jan Yuen, Simon Fidler, Sanja |
| contents | High-quality human motion data is becoming increasingly important for applications in robotics, simulation, and entertainment. Recent generative models offer a potential data source, enabling human motion synthesis through intuitive inputs like text prompts or kinematic constraints on poses. However, the small scale of public mocap datasets has limited the motion quality, control accuracy, and generalization of these models. In this work, we introduce Kimodo, an expressive and controllable kinematic motion diffusion model trained on 700 hours of optical motion capture data. Our model generates high-quality motions while being easily controlled through text and a comprehensive suite of kinematic constraints including full-body keyframes, sparse joint positions/rotations, 2D waypoints, and dense 2D paths. This is enabled through a carefully designed motion representation and two-stage denoiser architecture that decomposes root and body prediction to minimize motion artifacts while allowing for flexible constraint conditioning. Experiments on the large-scale mocap dataset justify key design decisions and analyze how the scaling of dataset size and model size affect performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15546 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Kimodo: Scaling Controllable Human Motion Generation Rempe, Davis Petrovich, Mathis Yuan, Ye Zhang, Haotian Peng, Xue Bin Jiang, Yifeng Wang, Tingwu Iqbal, Umar Minor, David de Ruyter, Michael Li, Jiefeng Tessler, Chen Lim, Edy Jeong, Eugene Wu, Sam Hassani, Ehsan Huang, Michael Yu, Jin-Bey Chung, Chaeyeon Song, Lina Dionne, Olivier Kautz, Jan Yuen, Simon Fidler, Sanja Computer Vision and Pattern Recognition Graphics Robotics High-quality human motion data is becoming increasingly important for applications in robotics, simulation, and entertainment. Recent generative models offer a potential data source, enabling human motion synthesis through intuitive inputs like text prompts or kinematic constraints on poses. However, the small scale of public mocap datasets has limited the motion quality, control accuracy, and generalization of these models. In this work, we introduce Kimodo, an expressive and controllable kinematic motion diffusion model trained on 700 hours of optical motion capture data. Our model generates high-quality motions while being easily controlled through text and a comprehensive suite of kinematic constraints including full-body keyframes, sparse joint positions/rotations, 2D waypoints, and dense 2D paths. This is enabled through a carefully designed motion representation and two-stage denoiser architecture that decomposes root and body prediction to minimize motion artifacts while allowing for flexible constraint conditioning. Experiments on the large-scale mocap dataset justify key design decisions and analyze how the scaling of dataset size and model size affect performance. |
| title | Kimodo: Scaling Controllable Human Motion Generation |
| topic | Computer Vision and Pattern Recognition Graphics Robotics |
| url | https://arxiv.org/abs/2603.15546 |