ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks

• URL: http://arxiv.org/abs/2511.12267v1
• Date: Sat, 15 Nov 2025 15:47:46 GMT
• Title: ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks
• Authors: Ruixun Liu, Bowen Fu, Jiayi Song, Kaiyu Li, Wanchen Li, Lanxuan Xue, Hui Qiao, Weizhan Zhang, Deyu Meng, Xiangyong Cao,
• Abstract summary: Existing dynamic resolution and token pruning methods are constrained by a passive perception paradigm.<n>We present LRS-GRO, a large-scale benchmark dataset tailored for active perception in UHR RS processing.<n>We propose ZoomEarth, an adaptive cropping-zooming framework with a novel Region-Guided reward that provides fine-grained guidance.
• Score: 49.99788276124186
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ultra-high-resolution (UHR) remote sensing (RS) images offer rich fine-grained information but also present challenges in effective processing. Existing dynamic resolution and token pruning methods are constrained by a passive perception paradigm, suffering from increased redundancy when obtaining finer visual inputs. In this work, we explore a new active perception paradigm that enables models to revisit information-rich regions. First, we present LRS-GRO, a large-scale benchmark dataset tailored for active perception in UHR RS processing, encompassing 17 question types across global, region, and object levels, annotated via a semi-automatic pipeline. Building on LRS-GRO, we propose ZoomEarth, an adaptive cropping-zooming framework with a novel Region-Guided reward that provides fine-grained guidance. Trained via supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO), ZoomEarth achieves state-of-the-art performance on LRS-GRO and, in the zero-shot setting, on three public UHR remote sensing benchmarks. Furthermore, ZoomEarth can be seamlessly integrated with downstream models for tasks such as cloud removal, denoising, segmentation, and image editing through simple tool interfaces, demonstrating strong versatility and extensibility.

Related papers

• GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery [69.05066425853326]
  "thinking-with-images" paradigm enables multimodal large language models (MLLMs) to actively explore visual scenes via zoom-in tools.<n>This is essential for ultra-high-resolution (UHR) remote sensing VQA, where task-relevant cues are sparse and tiny.<n>We propose GeoEyes, a training framework consisting of (1) a cold-start SFT dataset, UHR Chain-of-Zoom (UHR-CoZ), which covers diverse zooming regimes, and (2) an agentic reinforcement learning method, AdaZoom-GRPO, that explicitly rewards evidence gain and answer improvement during zoom
  arXiv  Detail & Related papers  (2026-02-15T15:50:55Z)
• GRASP: Guided Region-Aware Sparse Prompting for Adapting MLLMs to Remote Sensing [50.961694646995376]
  We propose a parameter-efficient fine-tuning (PEFT) strategy called Guided Region-Aware Sparse Prompting (GRASP)<n>GRASP introduces spatially structured soft prompts associated with spatial blocks extracted from a frozen visual token grid.<n>Experiments on multiple RSVQA benchmarks show that GRASP achieves competitive performance compared to existing fine-tuning and prompt-based methods.
  arXiv  Detail & Related papers  (2026-01-23T10:12:59Z)
• RS-ISRefiner: Towards Better Adapting Vision Foundation Models for Interactive Segmentation of Remote Sensing Images [17.648922817109224]
  RS-ISRefiner is a novel click-based IIS framework tailored for remote sensing images.<n>It consistently outperforms state-of-the-art IIS methods in terms of segmentation accuracy, efficiency and interaction cost.
  arXiv  Detail & Related papers  (2025-11-30T04:12:43Z)
• Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Images [51.74614065919118]
  This paper introduces SegEarth-OV, the first framework for annotation-free open-vocabulary segmentation of RS images.<n>We propose SimFeatUp, a universal upsampler that robustly restores high-resolution spatial details from coarse features.<n>We also present a simple yet effective Global Bias Alleviation operation to subtract the inherent global context from patch features.
  arXiv  Detail & Related papers  (2025-08-25T14:22:57Z)
• GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing [5.653111274028541]
  We propose GeoMag, an end-to-end general-purpose large model framework for remote sensing.<n>GeoMag focuses the attention scope based on prompt semantics to effectively perform remote sensing image parsing.<n>This approach improves the model's perception of critical target regions, suppresses background redundancy, and reduces the computational cost of interpreting high-resolution RS imagery.
  arXiv  Detail & Related papers  (2025-07-08T11:21:03Z)
• SeG-SR: Integrating Semantic Knowledge into Remote Sensing Image Super-Resolution via Vision-Language Model [38.06930079816157]
  High-resolution (HR) remote sensing imagery plays a vital role in a wide range of applications, including urban planning and environmental monitoring.<n>Due to limitations in sensors and data transmission links, the images acquired in practice often suffer from resolution degradation.<n>Remote Sensing Image Super-Resolution (RSISR) aims to reconstruct HR images from low-resolution (LR) inputs, providing a cost-effective and efficient alternative to direct HR image acquisition.
  arXiv  Detail & Related papers  (2025-05-29T02:38:34Z)
• GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing [32.85223015863783]
  GeoPixel is an end-to-end high resolution RS-LMM that supports pixel-level grounding.<n>It supports up to 4K HD resolution in any aspect ratio, ideal for high-precision RS image analysis.<n>GeoPixel demonstrates superior performance in pixel-level comprehension, surpassing existing LMMs in both single-target and multi-target segmentation tasks.
  arXiv  Detail & Related papers  (2025-01-23T18:59:30Z)
• RS-Mamba for Large Remote Sensing Image Dense Prediction [58.12667617617306]
  We propose the Remote Sensing Mamba (RSM) for dense prediction tasks in large VHR remote sensing images. RSM is specifically designed to capture the global context of remote sensing images with linear complexity. Our model achieves better efficiency and accuracy than transformer-based models on large remote sensing images.
  arXiv  Detail & Related papers  (2024-04-03T12:06:01Z)
• Recursive Generalization Transformer for Image Super-Resolution [108.67898547357127]
  We propose the Recursive Generalization Transformer (RGT) for image SR, which can capture global spatial information and is suitable for high-resolution images. We combine the RG-SA with local self-attention to enhance the exploitation of the global context. Our RGT outperforms recent state-of-the-art methods quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2023-03-11T10:44:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.