Safety
Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes
arXiv:2610.18356v1 Announce Type: new Abstract: City-scale 3D grounding is commonly formulated as candidate ranking, which requires precomputed instance proposals and becomes inefficient in large outd
arXiv:2610.18356v1 Announce Type: new Abstract: City-scale 3D grounding is commonly formulated as candidate ranking, which requires precomputed instance proposals and becomes inefficient in large outdoor scenes. We propose Urbex, an agentic vision-language framework that instead casts grounding as active spatial search. Urbex represents a city-scale 3D scene as an interactive multi-view environment, allowing a VLM agent to query landmarks, zoom into local regions, render oblique views, and commit a grounded bounding box. We optimize this tool-use policy with reinforcement learning on CityRefer, using smooth localization rewards and lightweight shaping rewards for efficient exploration. Experiments show that Urbex achieves the best Hit@1 and IoU on CityRefer, supports candidate-free grounding without ground-truth boxes, and is substantially faster than the strongest city-scale ranking baseline. Zero-shot results on STPLS3D-Refer further indicate improved cross-scene robustness.
Related
- UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scale
- Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes
- Agentic Building-Aware Satellite Gaussian Splatting for Auditable Urban DSM Reconstruction
Source: arXiv cs.CV | 2026-10-14