mlsanityData to 14 Oct 2026

SATGround: A Spatially-Aware Approach for Visual Grounding in Remote Sensing

arXiv 2512.08881 ↗First posted 9 Dec 2025cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

Vision-language models (VLMs) are emerging as powerful generalist tools for remote sensing, capable of integrating information across diverse tasks and enabling flexible, instruction-based interactions via a chat interface. In this work, we enhance VLM-based visual grounding in satellite imagery by proposing a novel structured localization mechanism. Our approach involves finetuning a pretrained VLM on a diverse set of instruction-following tasks, while interfacing a dedicated grounding module through specialized control tokens for localization. This method facilitates joint reasoning over both language and spatial information, significantly enhancing the model's ability to precisely localize objects in complex satellite scenes. We evaluate our framework on several remote sensing benchmarks, consistently improving the state-of-the-art, including a 33.2% relative improvement over previous methods on visual grounding. Our results highlight the benefits of integrating structured spatial reasoning into VLMs, paving the way for more reliable real-world satellite data analysis. Code will be released upon acceptance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 60 of its 78 references that are in the map. First posted on arXiv 9 Dec 2025.

Builds on

60 of 78 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues19 Dec
  2. 2024LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model4 Feb
  3. 2024EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain30 Jan
  4. 2024SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model18 Jan
  5. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensing24 Nov
  6. 2023RSGPT: A Remote Sensing Vision Language Model and Benchmark28 Jul
  7. 2023Vision-Language Models in Remote Sensing: Current Progress and Future Trends9 May
  8. 2021PointCLIP: Point Cloud Understanding by CLIP4 Dec

Other references · 52

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2023Visual Instruction Tuningcited by 7,869
  7. 2020End-to-End Object Detection with Transformerscited by 7,414
  8. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  10. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  11. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  12. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
38 more
  1. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  2. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
  3. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  4. 2015Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Modelscited by 1,362
  5. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
  6. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,216
  7. 2021Grounded Language-Image Pre-trainingcited by 1,156
  8. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,089
  9. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 906
  10. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 906
  11. 2023Vision-Language Models for Vision Tasks: A Surveycited by 839
  12. 2021Florence: A New Foundation Model for Computer Visioncited by 804
  13. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 797
  14. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  15. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 708
  16. 2023Instruction Tuning with GPT-4cited by 686
  17. 2021FILIP: Fine-grained Interactive Language-Image Pre-Trainingcited by 627
  18. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 625
  19. 2023Ferret: Refer and Ground Anything Anywhere at Any Granularitycited by 509
  20. 2022Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Modelcited by 317
  21. 2021A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Modelcited by 223
  22. 2020RSVQA: Visual Question Answering for Remote Sensing Datacited by 203
  23. 2023LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agentscited by 193
  24. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 187
  25. 2020FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understandingcited by 181
  26. 2015End-to-end people detection in crowded scenescited by 140
  27. 2024Tokenization counts: the impact of tokenization on arithmetic in frontier LLMscited by 115
  28. 2023BuboGPT: Enabling Visual Grounding in Multi-Modal LLMscited by 114
  29. 2021Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localizationcited by 113
  30. 2023LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Modelscited by 113
  31. 2022DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentationcited by 78
  32. 2024TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Datacited by 70
  33. 2023Positional Description Matters for Transformers Arithmeticcited by 56
  34. 2024SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentationcited by 41
  35. 2022From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Datacited by 39
  36. 2022HIT-UAV: A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detectioncited by 34
  37. 2024NumeroLogic: Number Encoding for Enhanced LLMs' Numerical Reasoningcited by 31
  38. 2022Learning to Discover and Detect Objectscited by 11

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding
  2. 2026RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning
  3. 2026GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision
  4. 2026Training-Free Open-Vocabulary Visual Grounding for Remote Sensing Images and Videos
  5. 2026Knowing Whether, Not Just Where: Anchor-Probing Distillation for Open-Set Remote Sensing Visual Grounding
  6. 2025RSVG-ZeroOV: Exploring a Training-Free Framework for Zero-Shot Open-Vocabulary Visual Grounding in Remote Sensing Images
  7. 2025Foundation Models for Remote Sensing: An Analysis of MLLMs for Object Localization
  8. 2026More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe