Salvato in:
Dettagli Bibliografici
Autori principali: Dai, Minyue, Fan, Ke, Rao, Anyi, Wang, Jingbo, Dai, Bo
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