Skip to main content
GameDev.net gamedev.net

Gesture Generation News

The latest Gesture Generation coverage curated for game developers.

EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation

A new motion-generation method uses speech cues to decide which gesture frames to mask, aiming to produce more natural co-speech animation. EchoMask builds a shared motion-audio space, then scores frame-level …

Research arXiv cs.GR · 4 weeks, 2 days ago
GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling

A new co-speech gesture system aims to make digital humans move more naturally while cutting inference from dozens of steps to a faster flow-matching pipeline. GestureLSM models body-region interactions with …

Research arXiv cs.GR · 4 weeks, 2 days ago
The GENEA Challenge 2026: A Large-Scale Disentangled Evaluation of Speech-Driven Gesture Generation on the Seamless Interaction Dataset

A new GENEA Challenge benchmark pushed speech-driven gesture generation through four large-scale human studies, with more than 23,000 votes from 869 testers. The results were sobering: motion realism improved on …

Research arXiv cs.GR · 1 month ago
StreamTalk: Streaming Co-Speech Gesture Generation with Key-Pose Anchoring

StreamTalk tackles a familiar real-time animation problem: gesture drift in streaming co-speech generation. The system adds a key-pose anchor at the end of each clip, then retrieves and refines motion …

Research arXiv cs.GR · 1 month, 1 week ago
SICAGE: Speaker-Independent Culture-Aware Gesture Generation using TED4C-L Dataset

A 106-hour, 764-speaker dataset is the main practical contribution here, because it lets gesture models be tested with speaker-disjoint splits instead of accidentally learning one person’s style. The paper argues …

Research arXiv cs.GR · 2 months, 2 weeks ago
PersonaGest: Personalized Co-Speech Gesture Generation with Semantic-Guided Hierarchical Motion Representation

PersonaGest introduces a novel approach to co-speech gesture generation, enhancing realism and personalization for developers in graphics and animation. By leveraging a two-stage framework that separates motion content from style, …

Research arXiv cs.GR · 4 months ago
Towards Unified Co-Speech Gesture Generation via Hierarchical Implicit Periodicity Learning

The introduction of Hierarchical Implicit Periodicity (HIP) learning marks a significant advancement in generating realistic co-speech gestures for 3D avatars. This method addresses the limitations of existing models by effectively …

Research arXiv cs.GR · 9 months ago