GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision

• URL: http://arxiv.org/abs/2607.01050v2
• Date: Sat, 04 Jul 2026 14:44:44 GMT
• Title: GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision
• Abstract summary: High-resolution remote sensing images usually cover large-scale scenes, where targets are often extremely small and surrounded by numerous visually similar distractors.<n>Existing MLLM-based methods usually formulate RSVG as one-step coordinate generation, which may lead to unstable predictions for small-object localization and complex queries.<n>We propose GeoSearcher, which reformulates RSVG as an anchor-guided progressive reasoning process and realizes it through two coupled stages.<n>In ACR-SFT, anchor-centric reasoning data are used to teach the model to represent key visual clues as anchors and progressively integrate location, relational, and attribute
• Score: 12.717046652815027
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent multimodal large language models (MLLMs) have shown strong cross-modal understanding and coordinate generation abilities in visual grounding. However, transferring these abilities to remote sensing visual grounding (RSVG) remains challenging. High-resolution remote sensing images usually cover large-scale scenes, where targets are often extremely small and surrounded by numerous visually similar distractors. Meanwhile, queries often contain multiple clues, such as reference objects, spatial relations, and target attributes. Existing MLLM-based methods usually formulate RSVG as one-step coordinate generation, which may lead to unstable predictions for small-object localization and complex queries. To address these challenges, we propose GeoSearcher, which reformulates RSVG as an anchor-guided progressive reasoning process and realizes it through two coupled stages: Anchor-Centric Reasoning Supervised Fine-Tuning (ACR-SFT) and Process-Faithful Group Relative Policy Optimization (PF-GRPO). In ACR-SFT, anchor-centric reasoning data are used to teach the model to represent key visual clues as anchors and progressively integrate location, relational, and attribute clues around them. In PF-GRPO, Process-Aware Reward (PAR) and Reasoning-Informative Sample Selector (RISS) further optimize this reasoning behavior by jointly evaluating key reasoning steps and target localization, while focusing training on samples that are more beneficial for improving progressive reasoning. Through this design, GeoSearcher transforms large-scale visual search into a more constrained local reasoning process. Extensive experiments on DIOR-RSVG, OPT-RSVG, and VRS-Bench show that GeoSearcher outperforms existing state-of-the-art methods. The project will be released at https://github.com/wangdianyu954-xixi/GeoSearcher.

Related papers

• Beyond Zooming: Learning Multi-Tool Visual Reasoning for Ultra-High-Resolution Remote Sensing [24.62771308673739]
  We introduce GeoMTVR, a large-scale Multi-Tool Visual Reasoning dataset built from wide-area satellite imagery.<n>By combining SFT on GeoMTVR with our RL algorithm, we develop GeoLens, a multi-tool visual reasoning MLLM for UHR RS.<n>Experiments show that GeoLens consistently outperforms direct reasoning and single-tool zoom-in baselines.
  arXiv  Detail & Related papers  (2026-07-28T17:09:16Z)
• GeoVista: Visually Grounded Active Perception for Ultra-High-Resolution Remote Sensing Understanding [13.76788623862368]
  Interpreting ultra-high-resolution (UHR) remote sensing images requires models to search for sparse and tiny visual evidence across large-scale scenes.<n>Existing 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.<n>We propose GeoVista, a planning-driven active perception framework for UHR remote sensing interpretation.
  arXiv  Detail & Related papers  (2026-05-14T07:15:46Z)
• Thinking with Geometry: Active Geometry Integration for Spatial Reasoning [68.59084007360615]
  We propose GeoThinker, a framework that shifts paradigm passive fusion to active perception.<n>Instead of feature mixing, GeoThinker enables the model to selectively retrieve geometric evidence conditioned on its internal reasoning demands.<n>Our results indicate that the ability to actively integrate spatial structures is essential for next-generation spatial intelligence.
  arXiv  Detail & Related papers  (2026-02-05T18:59:32Z)
• RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning [61.84363374647606]
  Remote Sensing Visual Grounding (RSVG) aims to localize target objects in large-scale aerial imagery based on natural language descriptions.<n>These descriptions often rely heavily on positional cues, posing unique challenges for Multimodal Large Language Models (MLLMs) in spatial reasoning.<n>We propose a reasoning-guided, position-aware post-training framework, dubbed textbfRSGround-R1, to progressively enhance spatial understanding.
  arXiv  Detail & Related papers  (2026-01-29T12:35:57Z)
• 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)
• GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding [23.253648429114236]
  We propose GeoViS, a progressive search-and-reasoning framework for remote sensing visual grounding.<n>We show that GeoViS consistently surpasses existing methods across key visual grounding metrics.
  arXiv  Detail & Related papers  (2025-12-02T12:45:52Z)
• GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization [53.080882980294795]
  Current research on agentic visual reasoning enables deep multimodal understanding but primarily focuses on image manipulation tools.<n>In this work, we revisit the geolocalization task, which requires not only nuanced visual grounding but also web search to confirm or refine hypotheses.<n>Since existing geolocalization benchmarks fail to meet the need for high-resolution imagery and the localization challenge for deep agentic reasoning, we curate GeoBench.<n>We propose GeoVista, an agentic model that seamlessly integrates tool invocation within the reasoning loop, including an image-zoom-in tool to magnify regions of interest and a web-search tool to retrieve related
  arXiv  Detail & Related papers  (2025-11-19T18:59:22Z)
• Exploring Efficient Open-Vocabulary Segmentation in the Remote Sensing [55.291219073365546]
  Open-Vocabulary Remote Sensing Image (OVRSIS) is an emerging task that adapts Open-Vocabulary (OVS) to the remote sensing (RS) domain.<n>textbfRSKT-Seg is a novel open-vocabulary segmentation framework tailored for remote sensing.<n> RSKT-Seg consistently outperforms strong OVS baselines by +3.8 mIoU and +5.9 mACC, while achieving 2x faster inference through efficient aggregation.
  arXiv  Detail & Related papers  (2025-09-15T15:24:49Z)
• Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework [51.26566634946208]
  We introduce smileGeo, a novel visual geo-localization framework. By inter-agent communication, smileGeo integrates the inherent knowledge of these agents with additional retrieved information. Results show that our approach significantly outperforms current state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-08-21T03:31:30Z)
• Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information [15.32353270625554]
  Cross-modal remote sensing text-image retrieval (RSCTIR) has recently become an urgent research hotspot due to its ability of enabling fast and flexible information extraction on remote sensing (RS) images. We first propose a novel RSCTIR framework based on global and local information (GaLR), and design a multi-level information dynamic fusion (MIDF) module to efficaciously integrate features of different levels. Experiments on public datasets strongly demonstrate the state-of-the-art performance of GaLR methods on the RSCTIR task.
  arXiv  Detail & Related papers  (2022-04-21T03:18:09Z)
• Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images [28.560068780733342]
  A novel context aggregation network (CATNet) is proposed to improve the feature extraction process. The proposed model exploits three lightweight plug-and-play modules, namely dense feature pyramid network (DenseFPN), spatial context pyramid ( SCP), and hierarchical region of interest extractor (HRoIE)
  arXiv  Detail & Related papers  (2021-11-22T08:55:25Z)

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.