Vision-language models (VLMs) have shown promise in earth observation (EO), yet they struggle with tasks that require grounding complex spatial reasoning in precise pixel-level visual representations. To address this problem, we introduce TerraScope, a unified VLM that delivers pixel-grounded geospatial reasoning with two key capabilities: (1) modality-flexible reasoning: it handles single-modality inputs (optical or SAR) and adaptively fuses different modalities into the reasoning process when both are available; (2) multi-temporal reasoning: it integrates temporal sequences for change analysis across multiple time points. In addition, we curate Terra-CoT, a large-scale dataset containing 1 million samples with pixel-level masks embedded in reasoning chains across multiple sources. We also propose TerraScope-Bench, the first benchmark for pixel-grounded geospatial reasoning with six sub-tasks that evaluates both answer accuracy and mask quality to ensure authentic pixel-grounded reasoning. Experiments show that TerraScope significantly outperforms existing VLMs on pixel-grounded geospatial reasoning while providing interpretable visual evidence.
@article{arxiv.2603.19039,
title = {TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation},
author = {Yan Shu and Bin Ren and Zhitong Xiong and Xiao Xiang Zhu and Begüm Demir and Nicu Sebe and Paolo Rota},
journal= {arXiv preprint arXiv:2603.19039},
year = {2026}
}