GeoVista: Visually Grounded Active Perception for Ultra-High-Resolution Remote Sensing Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909042036703232 |
|---|---|
| author | Zhu, Jiashun Fu, Ronghao Hu, Jiasen Xing, Nachuan Na, Xu Yang, Xiao Lin, Zhiwen Zhang, Weipeng Sun, Lang Xue, Zhiheng Liu, Haoran Zhang, Weijie Yang, Bo |
| author_facet | Zhu, Jiashun Fu, Ronghao Hu, Jiasen Xing, Nachuan Na, Xu Yang, Xiao Lin, Zhiwen Zhang, Weipeng Sun, Lang Xue, Zhiheng Liu, Haoran Zhang, Weijie Yang, Bo |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14475 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GeoVista: Visually Grounded Active Perception for Ultra-High-Resolution Remote Sensing Understanding Zhu, Jiashun Fu, Ronghao Hu, Jiasen Xing, Nachuan Na, Xu Yang, Xiao Lin, Zhiwen Zhang, Weipeng Sun, Lang Xue, Zhiheng Liu, Haoran Zhang, Weijie Yang, Bo Computer Vision and Pattern Recognition 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 |
| title | GeoVista: Visually Grounded Active Perception for Ultra-High-Resolution Remote Sensing Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.14475 |