Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2603.19795 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912975923707904 |
|---|---|
| author | Dai, Minyue Fan, Ke Rao, Anyi Wang, Jingbo Dai, Bo |
| author_facet | Dai, Minyue Fan, Ke Rao, Anyi Wang, Jingbo Dai, Bo |
| contents | Text-to-motion (T2M) generation is becoming a practical tool for animation and interactive avatars. However, modifying specific body parts while maintaining overall motion coherence remains challenging. Existing methods typically rely on cumbersome, high-dimensional joint constraints (e.g., trajectories), which hinder user-friendly, iterative refinement. To address this, we propose Modular Body-Part Phase Control, a plug-and-play framework enabling structured, localized editing via a compact, scalar-based phase interface. By modeling body-part latent motion channels as sinusoidal phase signals characterized by amplitude, frequency, phase shift, and offset, we extract interpretable codes that capture part-specific dynamics. A modular Phase ControlNet branch then injects this signal via residual feature modulation, seamlessly decoupling control from the generative backbone. Experiments on both diffusion- and flow-based models demonstrate that our approach provides predictable and fine-grained control over motion magnitude, speed, and timing. It preserves global motion coherence and offers a practical paradigm for controllable T2M generation. Project page: https://jixiii.github.io/bp-phase-project-page/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_19795 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Controllable Text-to-Motion Generation via Modular Body-Part Phase Control Dai, Minyue Fan, Ke Rao, Anyi Wang, Jingbo Dai, Bo Computer Vision and Pattern Recognition Text-to-motion (T2M) generation is becoming a practical tool for animation and interactive avatars. However, modifying specific body parts while maintaining overall motion coherence remains challenging. Existing methods typically rely on cumbersome, high-dimensional joint constraints (e.g., trajectories), which hinder user-friendly, iterative refinement. To address this, we propose Modular Body-Part Phase Control, a plug-and-play framework enabling structured, localized editing via a compact, scalar-based phase interface. By modeling body-part latent motion channels as sinusoidal phase signals characterized by amplitude, frequency, phase shift, and offset, we extract interpretable codes that capture part-specific dynamics. A modular Phase ControlNet branch then injects this signal via residual feature modulation, seamlessly decoupling control from the generative backbone. Experiments on both diffusion- and flow-based models demonstrate that our approach provides predictable and fine-grained control over motion magnitude, speed, and timing. It preserves global motion coherence and offers a practical paradigm for controllable T2M generation. Project page: https://jixiii.github.io/bp-phase-project-page/ |
| title | Controllable Text-to-Motion Generation via Modular Body-Part Phase Control |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.19795 |