GeoVista: Visually Grounded Active Perception for Ultra-High-Resolution Remote Sensing Understanding

TL;DR

GeoVista introduces a planning-driven active perception framework for ultra-high-resolution remote sensing images, enabling global exploration, multi-region inspection, and evidence aggregation to improve understanding.

Contribution

It proposes a novel global planning and local verification approach, along with a new trajectory corpus, for more effective remote sensing image interpretation.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Effectively verifies multiple candidate regions through branch-wise inspection.

Maintains explicit evidence state for cross-region aggregation and de-duplication.

Abstract

Interpreting ultra-high-resolution (UHR) remote sensing images requires models to search for sparse and tiny visual evidence across large-scale scenes. Existing remote sensing vision-language models can inspect local regions with zooming and cropping tools, but most exploration strategies follow either a one-shot focus or a single sequential trajectory. Such single-path exploration can lose global context, leave scattered regions unvisited, and revisit or count the same evidence multiple times. To this end, we propose GeoVista, a planning-driven active perception framework for UHR remote sensing interpretation. Instead of committing to one zooming path, GeoVista first builds a global exploration plan, then verifies multiple candidate regions through branch-wise local inspection, while maintaining an explicit evidence state for cross-region aggregation and de-duplication. To enable this behavior, we introduce APEX-GRO, a cold-start supervised trajectory corpus that reformulates diverse UHR tasks as Global-Region-Object interactive reasoning processes with a unified, scale-invariant spatial representation. We further design an Observe-Plan-Track mechanism for global observation, adaptive region inspection, and evidence tracking, and align the model with a GRPO-based strategy using step-wise rewards for planning, localization, and final answer correctness. Experiments on RSHR-Bench, XLRS-Bench, and LRS-VQA show that GeoVista achieves state-of-the-art performance. Code and dataset are available at https://github.com/ryan6073/GeoVista