Urbex:面向城市級 3D 場景的智能體式空間定位
Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes
Urbex 提出面向城市級 3D 場景的智能體視覺語言框架,把空間定位由候選排序改為主動搜尋。框架在 CityRefer 上透過強化學習優化工具使用策略,取得最佳 Hit@1 和 IoU,並支援無需候選框及真值框的定位,速度大幅快於最強城市級排序基線。STPLS3D-Refer 的 zero-shot 結果亦顯示其跨場景穩健性有所提升。
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.
View arXiv page View PDF Project page GitHub 3 Add to collection
Get this paper in your agent:
hf papers read 2610.18356
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 1
Image-Text-to-Text • 4B • Updated 43 minutes ago • 3vvangfaye/Urbex-4B
Datasets citing this paper 1
vvangfaye/Urbex-Data
Viewer • Updated 43 minutes ago • 43 • 2
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.18356 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co