Geospatial vector geometry improves spatial reasoning in vision language models
Geospatial Vector Geometry as a Native Spatial Modality for Vision-Language Models
Artificial Intelligence
Summary
Understanding and reasoning about space in vision-language models is hard when looking at large geographic areas because they mostly rely on pictures and words. The authors found that using geospatial vector geometry as a built-in way to represent spatial information helps these models understand space better. They created a new model called GeoVec-VLM that uses this approach to connect geometry with images and language, improving accuracy by about 11 percent on spatial tasks. This method also works well when applied to new geographic areas and keeps spatial relationships more consistent.
What this means in practice
- •For mapping software developers: Integrate geospatial vector geometry to improve map-based query answering and spatial reasoning across varied geographic scales.
- •For urban planning teams: Use GeoVec-VLM to support accurate spatial reasoning about city layouts and infrastructure from limited visual and language inputs.
Authors
Huang Fei, Boyi Chen, Hao Xue, Yang Yue, Yehong Xu, Xiaofang Zhou
Abstract
Geospatial reasoning links VLMs to real-world action and decision making. Reliable reasoning requires accurate spatial information and effective spatial representations. However, current VLMs obtain this information mainly from language and vision. At larger geographic scales, limited visual observations make it difficult to establish accurate spatial references and recover precise spatial relations. This leads to a bottleneck for VLM spatial perception and reasoning. This paper proposes that geospatial vector geometry can become a native spatial modality within a VLM and introduces GeoVec-VLM. First, we develop a structured geometry representation that preserves the spatial structure and arrangement of vector objects, building an explicit spatial basis. Second, we introduce a geometry interaction strategy that brings this basis into multimodal computation, where it interacts with visual content and language references according to the queried spatial relations. Together, these designs allow perception and reasoning to operate on shared geometric references. Across five spatial reasoning tasks, GeoVec-VLM improves mean accuracy by about 11\% relative to the strongest baseline, maintains its gains under geographic transfer, and shows greater geometric consistency. Our results show that geospatial vector geometry offers a promising internal spatial basis for VLM spatial reasoning. https://github.com/TXFR/GeoVector-VLM