HuggingFace Daily Papers·· 1 天前
Urbex：面向城市场景 3D 的智能体空间定位框架
Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes
AI 导读
Urbex 是一个智能体视觉语言框架，把城市级 3D 定位重构为主动空间搜索，让 VLM 智能体查询地标、缩放局部区域、渲染斜视角并输出定位框。该框架在 CityRefer 上通过强化学习优化工具调用策略，取得最佳 Hit@1 和 IoU，无需候选框与 ground-truth box，速度显著快于最强的城市级排序基线。在 STPLS3D-Refer 上的零样本结果进一步显示跨场景鲁棒性提升。
正文
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.
| Comments: | NeurIPS 2026. 23 pages, 10 figures. Code: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18356 [cs.CV] |
| (or arXiv:2610.18356v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18356 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wang Yu [view email]
[v1]
Tue, 13 Oct 2026 13:23:24 UTC (15,530 KB)
来源：HuggingFace Daily Papers · arxiv.org