eess.IVNov 14, 2026

XLSAR-Bench: Towards Extremely Large SAR Imagery Understanding of MLLMs

Authors: La Jiang, Lingfeng Chen, Jiaqi Zhu, Fengrong Guo, Jiehua Zhang, Panhe Hu, Li Liu, Zhen Liu

Organizations: College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha 410073, China · Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, 90570 Oulu, Finland

Abstract

The rapid development of multimodal large language models (MLLMs) has highlighted the need for comprehensive benchmarks to assess their capabilities and limitations in remote sensing (RS). However, evaluating MLLMs in large-size synthetic aperture radar (SAR) scenarios remains challenging, as understanding complete scenes requires both global semantic interpretation and fine-grained target perception. Existing SAR benchmarks predominantly rely on small image patches, limiting their ability to assess these capabilities jointly. To address these limitations, we present XLSAR-Bench, a comprehensive benchmark for evaluating the perception and reasoning capabilities of MLLMs in large-scene SAR imagery. XLSAR-Bench comprises 405 images with an average size of 7153×\times7153 pixels, ten tasks spanning visual question answering, visual grounding, and detailed image captioning, with all evaluation samples meticulously annotated manually, assisted by a semi-automatic captioner. Experimental results from general-purpose and domain-specific MLLMs reveal persistent challenges in understanding large SAR scenes and accurately perceiving small targets. We have open-sourced XLSAR-Bench to support further research in developing more powerful MLLMs for complete large SAR scenes.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?

    Jul 22, 2026Qiwei Ma, Chunping Qiu, Xinjun Cheng +5Remote Sensing Image UnderstandingRemote Sensing Visual Question Answering

  2. Towards a Large Language-Vision Question Answering Model for MSTAR Automatic Target Recognition

    May 11, 2026David F. Ramirez, Tim L. Overman, Kristen Jaskie +2Remote Sensing Image UnderstandingRemote Sensing Visual Question Answering