Article

GestureFM : Compact Latent Flow Matching for Low-Latency Co-Speech Body-Motion Generation

2026-08-14

Abstract excerpt

<title>Abstract</title> <p>Interactive digital humans require speech-driven body motion that can begin before a complete utterance is available, but many high-quality co-speech generation methods are designed for offline full-sequence inference. This study aims to generate SMPL-X body motion from speech with low first-chunk latency while maintaining competitive motion quality in streaming inference. We propose \o...

Topics

Open a Topic to create a Post that cites this publication.

Uncategorized literature

Identifiers and source

Literature Corpus work: 372193a6-be0b-507f-a510-98d2fac924a7
DOI: 10.21203/rs.3.rs-10338817/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

GestureFM : Compact Latent Flow Matching for Low-Latency Co-Speech Body-Motion GenerationDOI 10.21203/rs.3.rs-10338817/v1Read

HoloGest: Decoupled Diffusion and Motion Priors for Generating Holisticly Expressive Co-speech GesturesSemantic proximity Read

Towards Human-Centered and Efficient Video Synthesis: A Survey of Multimodal Diffusion ModelsSemantic proximity Read

3D-GS Talker: 3D Gaussian Based Audio-Driven Real-Time Talking Head GenerationSemantic proximity Read

Expanding Multilingual Co-Speech Interaction: The Impact of Enhanced Gesture Units in Text-to-Gesture Synthesis for Digital HumansSemantic proximity Read

Fusing Text-Speech Multimodal Cues with 2D Motion Priors: Boosting 3D Human Motion Generation for VR and AnimationSemantic proximity Read

Improving Text-Speech Driven 3D Human Motion Synthesis via 2D Data Augmentation and CLaM-Based Standardized EvaluationSemantic proximity Read

GrambaTalk: Generating 3D Talking Head with Spatial Graph and Temporal MambaSemantic proximity Read

A New Paradigm for Human Motion Generation Based on Cross-Modal Nested AlignmentSemantic proximity Read

A Unified Framework for Human Motion Generation with Multimodal InputsSemantic proximity Read

Advancements in Talking Head Generation: A Comprehensive Review of Techniques, Metrics, and ChallengesSemantic proximity Read

RAE-NeRF: Residual-Based Audio-Video Encoder with Denoising in Talking Head SynchronizationSemantic proximity Read

MiniCausal-T2V: Towards Ultra-Low Latency and Memory-Efficient Causal Video Generation on Edge DevicesSemantic proximity Read