| title | Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes |
|---|---|
| authors | Yu Wang, Rui Dai, Wei Chen, Yi Wang, Bo Dang, Kaikui Liu, Xiangxiang Chu, Yansheng Li |
| date | 2026-10-13 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.18356 |
| affiliation | alibaba |
| upvotes | 130 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| 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. |
cite
@misc{wang2026urbex,
title={Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes},
author={Yu Wang and Rui Dai and Wei Chen and Yi Wang and Bo Dang and Kaikui Liu and Xiangxiang Chu and Yansheng Li},
year={2026},
eprint={2610.18356},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.18356}
}