Article

GrambaTalk: Generating 3D Talking Head with Spatial Graph and Temporal Mamba

2026-05-19

Abstract excerpt

<title>Abstract</title> <p>Animating 3D head meshes from speech is important for applications like virtual avatars, VR and AR interaction, and digital humans. However, speech-driven facial animation requires modeling both rapid articulatory dynamics and spatially coherent mesh deformation, which remains challenging for existing methods that treat temporal modeling and geometric reasoning separately. We present Gr...

Topics

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

Identifiers and source

Literature Corpus work: af84cb96-e70b-566c-b6d0-5f37e4c00fb9
DOI: 10.21203/rs.3.rs-9623085/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

GrambaTalk: Generating 3D Talking Head with Spatial Graph and Temporal MambaDOI 10.21203/rs.3.rs-9623085/v1Read

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

3D head-talk: speech synthesis 3D head movement face animationSemantic proximity Read

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

Graph-Driven Micro-Expression Rendering with Emotionally Diverse Expressions for Lifelike Digital HumansSemantic proximity Read

GestureFM : Compact Latent Flow Matching for Low-Latency Co-Speech Body-Motion GenerationSemantic proximity Read

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

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

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

Mono-Splat: Real-Time Photorealistic Human Avatar Reconstruction from Monocular Webcam Video via Deformable 3D Gaussian SplattingSemantic proximity Read

A Novel Technique for Optimizing Volumetric Avatars: From 2D Images to Lightweight 3D ModelsSemantic proximity Read

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

Action Unit-Based 3D Face Reconstruction Using TransformersSemantic proximity Read