Jul 2026
DM-KG: A Novel Method for Boosting Spatial Cognition of Vision-Language Models in Street View Imagery
DM-KG (Direction-Metric Knowledge Graph), a structurally grounded spatial representation framework for street view imagery, is proposed, providing a flexible, generalized, and interpretable framework for geographic visual question answering (GeoVQA) in open environments.
Xin-Yue Xu, Zheng Zhang, Kunyang Ma et al.
· arXiv.org · 0 citations