Saved in:
Bibliographic Details
Main Authors: Chen, Jiahui, Huan, Yang, Shi, Runhua, Ding, Chanfan, Mo, Xiaoqi, Xiong, Siyu, He, Yinong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.21616
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913762703835136
author Chen, Jiahui
Huan, Yang
Shi, Runhua
Ding, Chanfan
Mo, Xiaoqi
Xiong, Siyu
He, Yinong
author_facet Chen, Jiahui
Huan, Yang
Shi, Runhua
Ding, Chanfan
Mo, Xiaoqi
Xiong, Siyu
He, Yinong
contents Gestures are essential for enhancing co-speech communication, offering visual emphasis and complementing verbal interactions. While prior work has concentrated on point-level motion or fully supervised data-driven methods, we focus on co-speech gestures, advocating for weakly supervised learning and pixel-level motion deviations. We introduce a weakly supervised framework that learns latent representation deviations, tailored for co-speech gesture video generation. Our approach employs a diffusion model to integrate latent motion features, enabling more precise and nuanced gesture representation. By leveraging weakly supervised deviations in latent space, we effectively generate hand gestures and mouth movements, crucial for realistic video production. Experiments show our method significantly improves video quality, surpassing current state-of-the-art techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2503_21616
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Audio-driven Gesture Generation via Deviation Feature in the Latent Space
Chen, Jiahui
Huan, Yang
Shi, Runhua
Ding, Chanfan
Mo, Xiaoqi
Xiong, Siyu
He, Yinong
Computer Vision and Pattern Recognition
Gestures are essential for enhancing co-speech communication, offering visual emphasis and complementing verbal interactions. While prior work has concentrated on point-level motion or fully supervised data-driven methods, we focus on co-speech gestures, advocating for weakly supervised learning and pixel-level motion deviations. We introduce a weakly supervised framework that learns latent representation deviations, tailored for co-speech gesture video generation. Our approach employs a diffusion model to integrate latent motion features, enabling more precise and nuanced gesture representation. By leveraging weakly supervised deviations in latent space, we effectively generate hand gestures and mouth movements, crucial for realistic video production. Experiments show our method significantly improves video quality, surpassing current state-of-the-art techniques.
title Audio-driven Gesture Generation via Deviation Feature in the Latent Space
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.21616