Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Xiangyue, Cai, Yiyi, Li, Kunhang, Yang, Kaixing, Zhou, You, Li, Zhengqing, Chu, Xuangeng, Zhang, Jiaxu, Liu, Haiyang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.06064
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913098690985984
author Zhang, Xiangyue
Cai, Yiyi
Li, Kunhang
Yang, Kaixing
Zhou, You
Li, Zhengqing
Chu, Xuangeng
Zhang, Jiaxu
Liu, Haiyang
author_facet Zhang, Xiangyue
Cai, Yiyi
Li, Kunhang
Yang, Kaixing
Zhou, You
Li, Zhengqing
Chu, Xuangeng
Zhang, Jiaxu
Liu, Haiyang
contents We propose PersonaGesture, a diffusion-based pipeline for single-reference co-speech gesture personalization of unseen speakers. Given target speech and one motion clip from a new speaker, the model must synthesize gestures that follow the new utterance while retaining speaker-specific pose choices, without per-speaker optimization. This setting is useful for avatars and virtual agents, but it is hard because the reference mixes stable speaker habits with utterance-specific trajectories. PersonaGesture consists of two key components, Adaptive Style Infusion (ASI) and Implicit Distribution Rectification (IDR), to separate temporal identity evidence from residual statistic correction. A Style Perceiver first encodes the variable-length reference into compact speaker-memory tokens. ASI injects these tokens into denoising through zero-initialized residual cross-attention, enabling style evidence to affect motion formation without replacing the pretrained speech-to-motion prior. Building on this, IDR applies a length-aware diagonal affine map in latent space to correct residual channel-wise moments estimated from the same reference. Across BEAT2 and ZeroEGGS, we evaluate quantitative metrics, reference-identity controls, same-audio diagnostics, qualitative comparisons, and human preference. Experiments show that separating denoising-time speaker memory from conservative post-generation moment correction improves unseen-speaker personalization over collapsed style codes, full-reference attention, and one-clip finetuning. Project: https://xiangyue-zhang.github.io/PersonaGesture.
format Preprint
id arxiv_https___arxiv_org_abs_2605_06064
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PersonaGesture: Single-Reference Co-Speech Gesture Personalization for Unseen Speakers
Zhang, Xiangyue
Cai, Yiyi
Li, Kunhang
Yang, Kaixing
Zhou, You
Li, Zhengqing
Chu, Xuangeng
Zhang, Jiaxu
Liu, Haiyang
Computer Vision and Pattern Recognition
We propose PersonaGesture, a diffusion-based pipeline for single-reference co-speech gesture personalization of unseen speakers. Given target speech and one motion clip from a new speaker, the model must synthesize gestures that follow the new utterance while retaining speaker-specific pose choices, without per-speaker optimization. This setting is useful for avatars and virtual agents, but it is hard because the reference mixes stable speaker habits with utterance-specific trajectories. PersonaGesture consists of two key components, Adaptive Style Infusion (ASI) and Implicit Distribution Rectification (IDR), to separate temporal identity evidence from residual statistic correction. A Style Perceiver first encodes the variable-length reference into compact speaker-memory tokens. ASI injects these tokens into denoising through zero-initialized residual cross-attention, enabling style evidence to affect motion formation without replacing the pretrained speech-to-motion prior. Building on this, IDR applies a length-aware diagonal affine map in latent space to correct residual channel-wise moments estimated from the same reference. Across BEAT2 and ZeroEGGS, we evaluate quantitative metrics, reference-identity controls, same-audio diagnostics, qualitative comparisons, and human preference. Experiments show that separating denoising-time speaker memory from conservative post-generation moment correction improves unseen-speaker personalization over collapsed style codes, full-reference attention, and one-clip finetuning. Project: https://xiangyue-zhang.github.io/PersonaGesture.
title PersonaGesture: Single-Reference Co-Speech Gesture Personalization for Unseen Speakers
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.06064