ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
ELSA3D is a unified 3D model designed to connect language understanding and 3D geometry generation through a shared backbone. It achieves this by structuring text and geometry reasoning across matched abstraction scales using 'Anchor Tokens' that sparsely link semantic cues to the most relevant geometric resolutions, leading to state-of-the-art performance.