Precise spatial understanding in Earth Observation is essential for translating raw aerial imagery into actionable insights for critical applications like urban planning, environmental monitoring and disaster management. However, Multimodal Large Language Models exhibit critical deficiencies in fine-grained spatial understanding within Remote Sensing, primarily due to a reliance on limited or repurposed legacy datasets. To bridge this gap, we introduce a large-scale dataset grounded in verifiable cadastral vector data, comprising 3.8 million annotated objects across 510k high-resolution images with 135 granular semantic categories. We validate this resource through a comprehensive instruction-tuning benchmark spanning seven spatial reasoning tasks. Our evaluation establishes a robust baseline using a standard LLaVA architecture. We show that while current RS-specialized and commercial models (e.g., Gemini) struggle in zero-shot settings, high-fidelity supervision effectively bridges this gap, enabling standard architectures to master fine-grained spatial grounding without complex architectural modifications.
@article{arxiv.2603.14609,
title = {GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector Data},
author = {Roger Ferrod and Maël Lecene and Krishna Sapkota and George Leifman and Vered Silverman and Genady Beryozkin and Sylvain Lobry},
journal= {arXiv preprint arXiv:2603.14609},
year = {2026}
}