AI RESEARCH
SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching
arXiv CS.CV
•
ArXi:2605.21788v1 Announce Type: new Zero-shot 3D visual grounding requires localizing objects in unstructured environments from free-form natural language. Recent vision-language model (VLM) approaches achieve promising results but rely on view-dependent reasoning or implicit representations, limiting spatial consistency and interpretability for compositional queries. We propose SceneGraphGrounder, a framework that reformulates 3D grounding as structured graph matching over a reconstructed 3D scene graph. To enable this formulation, we.