Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Guo, Yueqian, Li, Tianzhao, Lyu, Xin, Chen, Jiehaolin, Wang, Zhaohan, Xiao, Sirui, Chen, Yurun, He, Yezi, Li, Helin, Zhang, Fan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.01077
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915317685420032
author Guo, Yueqian
Li, Tianzhao
Lyu, Xin
Chen, Jiehaolin
Wang, Zhaohan
Xiao, Sirui
Chen, Yurun
He, Yezi
Li, Helin
Zhang, Fan
author_facet Guo, Yueqian
Li, Tianzhao
Lyu, Xin
Chen, Jiehaolin
Wang, Zhaohan
Xiao, Sirui
Chen, Yurun
He, Yezi
Li, Helin
Zhang, Fan
contents Large Language Model (LLM)-driven digital humans have sparked a series of recent studies on co-speech gesture generation systems. However, existing approaches struggle with real-time synthesis and long-text comprehension. This paper introduces Transformer-Based Rich Motion Matching (TRiMM), a novel multi-modal framework for real-time 3D gesture generation. Our method incorporates three modules: 1) a cross-modal attention mechanism to achieve precise temporal alignment between speech and gestures; 2) a long-context autoregressive model with a sliding window mechanism for effective sequence modeling; 3) a large-scale gesture matching system that constructs an atomic action library and enables real-time retrieval. Additionally, we develop a lightweight pipeline implemented in the Unreal Engine for experimentation. Our approach achieves real-time inference at 120 fps and maintains a per-sentence latency of 0.15 seconds on consumer-grade GPUs (Geforce RTX3060). Extensive subjective and objective evaluations on the ZEGGS, and BEAT datasets demonstrate that our model outperforms current state-of-the-art methods. TRiMM enhances the speed of co-speech gesture generation while ensuring gesture quality, enabling LLM-driven digital humans to respond to speech in real time and synthesize corresponding gestures. Our code is available at https://github.com/teroon/TRiMM-Transformer-Based-Rich-Motion-Matching
format Preprint
id arxiv_https___arxiv_org_abs_2506_01077
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TRiMM: Transformer-Based Rich Motion Matching for Real-Time multi-modal Interaction in Digital Humans
Guo, Yueqian
Li, Tianzhao
Lyu, Xin
Chen, Jiehaolin
Wang, Zhaohan
Xiao, Sirui
Chen, Yurun
He, Yezi
Li, Helin
Zhang, Fan
Graphics
Human-Computer Interaction
68U05(Primary), 62M45(Secondary)
Large Language Model (LLM)-driven digital humans have sparked a series of recent studies on co-speech gesture generation systems. However, existing approaches struggle with real-time synthesis and long-text comprehension. This paper introduces Transformer-Based Rich Motion Matching (TRiMM), a novel multi-modal framework for real-time 3D gesture generation. Our method incorporates three modules: 1) a cross-modal attention mechanism to achieve precise temporal alignment between speech and gestures; 2) a long-context autoregressive model with a sliding window mechanism for effective sequence modeling; 3) a large-scale gesture matching system that constructs an atomic action library and enables real-time retrieval. Additionally, we develop a lightweight pipeline implemented in the Unreal Engine for experimentation. Our approach achieves real-time inference at 120 fps and maintains a per-sentence latency of 0.15 seconds on consumer-grade GPUs (Geforce RTX3060). Extensive subjective and objective evaluations on the ZEGGS, and BEAT datasets demonstrate that our model outperforms current state-of-the-art methods. TRiMM enhances the speed of co-speech gesture generation while ensuring gesture quality, enabling LLM-driven digital humans to respond to speech in real time and synthesize corresponding gestures. Our code is available at https://github.com/teroon/TRiMM-Transformer-Based-Rich-Motion-Matching
title TRiMM: Transformer-Based Rich Motion Matching for Real-Time multi-modal Interaction in Digital Humans
topic Graphics
Human-Computer Interaction
68U05(Primary), 62M45(Secondary)
url https://arxiv.org/abs/2506.01077