Article

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

2025-11-17

Abstract excerpt

Text-speech guided 3D human motion synthesis has long faced two critical bottlenecks: inconsistent evaluation metrics that hinder reliable cross-method comparison, and the scarcity of high-quality 3D motion capture (MoCap) data that restricts model generalization. This study addresses both issues through an integrated framework. On the data side, it leverages abundant 2D motion data (building on the Motion-2-to-3...

Topics

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

Identifiers and source

Literature Corpus work: 34387fd9-33b2-58a3-9e26-688f536e37e2
DOI: 10.22541/au.176340983.34994517/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Improving Text-Speech Driven 3D Human Motion Synthesis via 2D Data Augmentation and CLaM-Based Standardized EvaluationDOI 10.22541/au.176340983.34994517/v1Read

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

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

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

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

Language-Driven 3D Skeleton-Based Motion Generation with Action Nesting GraphSemantic proximity Read

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

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

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

MotionCharacter: Identity-Preserving and Motion Controllable Human Video GenerationSemantic proximity Read