SOURCE-LINKED INTELLIGENCE

MoVT: Video-Augmented Motion Tokenizer for Text-to-Motion Generation

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Text-driven 3D human motion generation models face significant challenges in responding to diverse and unconstrained textual prompts, primarily due to the limited availability of 3D motion training data. To address this, we introduce MoVT, a novel framework that effectively leverages the extensive range of human action videos to enhance text-to-motion generation. At the core of our approach is the cross-modal augmented motion tokenizer, which projects discrete 3D motion tokens into the 2D domain. This projection allows us to enrich the motion codebook with complex, real-world motion patterns d

Read original source ↗ Open in workspace

recordType

paper

region

Global