GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling

[2501.18898] GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2501.18898 (cs) [Submitted on 31 Jan 2025 ( v1 ), last revised 15 Aug 2026 (this version, v4)] Title: GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling Authors: Pinxin Liu , Luchuan Song , Junhua Huang , Haiyang Liu , Junfan Zhu , Chenliang Xu View a PDF of the paper titled GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling, by Pinxin Liu and 5 other authors View PDF HTML (experimental) Abstract: Generating full-body human gestures based on speech signals remains challenges on quality and speed. Existing approaches model different body regions such as body, legs and hands separately, which fail to capture the spatial interactions between them and result in unnatural and disjointed movements. Additionally, their autoregressive/diffusion-based pipelines show slow generation speed due to dozens of inference steps. To address these two challenges, we propose GestureLSM, a flow-matching-based approach for Co-Speech Gesture Generation with spatial-temporal modeling. Our method i) explicitly model the interaction of tokenized body regions through spatial and temporal attention, for generating coherent full-body gestures. ii) introduce the flow matching to enable more efficient sampling by explicitly modeling the latent velocity space. To overcome the suboptimal performance of flow matching baseline, we propose latent shortcut learning and beta distribution time stamp sampling during training to enhance gesture synthesis quality and accelerate inference. Combining the spatial-temporal modeling and improved flow matching-based framework, GestureLSM achieves state-of-the-art performance on BEAT2 while significantly reducing inference time compared to existing methods, highlighting its potential for enhancing digital humans and embodied agents in real-world applications. Project Page: this https URL Comments: Accepted to ICCV 2025. Project Page: this https URL Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR) Cite as: arXiv:2501.18898 [cs.CV] (or arXiv:2501.18898v4 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2501.18898 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Pinxin Liu [ view email ] [v1] Fri, 31 Jan 2025 05:34:59 UTC (3,857 KB) [v2] Sat, 8 Mar 2025 01:34:25 UTC (15,484 KB) [v3] Sun, 3 Aug 2025 07:25:09 UTC (13,405 KB) [v4] Sat, 15 Aug 2026 03:16:14 UTC (13,399 KB) Full-text links: Access Paper: View a PDF of the paper titled GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling, by Pinxin Liu and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2025-01 Change to browse by: cs cs.GR References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• MotionSpaceFlow: Representation-Aware Flow Matching in Direct Motion Space#1119263
• DuoGesture: Motion-Grounded Semantic Conditioning and Biomechanical Beat Priors for Co-Speech Gesture Generation#924578
• DuoGesture: Motion-Grounded Semantic Conditioning and Biomechanical Beat Priors for Co-Speech Gesture Generation#920346
• Towards Fine-grained Temporal Perception: Post-Training Large Audio-Language Models with Audio-Side Time Prompt#14079
• WorldAttention: An Efficient Attention Architecture for Interactive Video World Models#1128868