Salvato in:
Dettagli Bibliografici
Autori principali: Sha, Xuanmeng, Zhang, Liyun, Mashita, Tomohiro, Chiba, Naoya, Uranishi, Yuki
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.18451
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914280900657152
author Sha, Xuanmeng
Zhang, Liyun
Mashita, Tomohiro
Chiba, Naoya
Uranishi, Yuki
author_facet Sha, Xuanmeng
Zhang, Liyun
Mashita, Tomohiro
Chiba, Naoya
Uranishi, Yuki
contents Generating holistic co-speech gestures that integrate full-body motion with facial expressions suffers from semantically incoherent coordination on body motion and spatially unstable meaningless movements due to existing part-decomposed or frame-level regression methods, We introduce 3DGesPolicy, a novel action-based framework that reformulates holistic gesture generation as a continuous trajectory control problem through diffusion policy from robotics. By modeling frame-to-frame variations as unified holistic actions, our method effectively learns inter-frame holistic gesture motion patterns and ensures both spatially and semantically coherent movement trajectories that adhere to realistic motion manifolds. To further bridge the gap in expressive alignment, we propose a Gesture-Audio-Phoneme (GAP) fusion module that can deeply integrate and refine multi-modal signals, ensuring structured and fine-grained alignment between speech semantics, body motion, and facial expressions. Extensive quantitative and qualitative experiments on the BEAT2 dataset demonstrate the effectiveness of our 3DGesPolicy across other state-of-the-art methods in generating natural, expressive, and highly speech-aligned holistic gestures.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18451
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle 3DGesPolicy: Phoneme-Aware Holistic Co-Speech Gesture Generation Based on Action Control
Sha, Xuanmeng
Zhang, Liyun
Mashita, Tomohiro
Chiba, Naoya
Uranishi, Yuki
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multimedia
Sound
I.3.7; I.2.10
Generating holistic co-speech gestures that integrate full-body motion with facial expressions suffers from semantically incoherent coordination on body motion and spatially unstable meaningless movements due to existing part-decomposed or frame-level regression methods, We introduce 3DGesPolicy, a novel action-based framework that reformulates holistic gesture generation as a continuous trajectory control problem through diffusion policy from robotics. By modeling frame-to-frame variations as unified holistic actions, our method effectively learns inter-frame holistic gesture motion patterns and ensures both spatially and semantically coherent movement trajectories that adhere to realistic motion manifolds. To further bridge the gap in expressive alignment, we propose a Gesture-Audio-Phoneme (GAP) fusion module that can deeply integrate and refine multi-modal signals, ensuring structured and fine-grained alignment between speech semantics, body motion, and facial expressions. Extensive quantitative and qualitative experiments on the BEAT2 dataset demonstrate the effectiveness of our 3DGesPolicy across other state-of-the-art methods in generating natural, expressive, and highly speech-aligned holistic gestures.
title 3DGesPolicy: Phoneme-Aware Holistic Co-Speech Gesture Generation Based on Action Control
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Multimedia
Sound
I.3.7; I.2.10
url https://arxiv.org/abs/2601.18451