Remote Sensing VQA

VQA: Visual Question Answering

Ask about this topic

Overview

Remote sensing VQA asks models to interpret Earth imagery and answer questions about objects, land use, spatial relationships, change over time, and measured quantities, supporting applications such as mapping and disaster monitoring. Common approaches adapt vision-language models through fine-tuning or lightweight adapters, while newer systems use localization, image tiling, retrieval, segmentation, or other tools to gather visual evidence. Benchmarks increasingly test high-resolution scenes, multiple sensors, video, temporal comparisons, and quantitative or spatial reasoning. A central challenge is making answers reliably grounded in the right image evidence: models still struggle with fine detail, numerical reasoning, and long-range or cross-view relations, while tool use and larger inputs can increase inference cost.

Latest papers

CardsList

36 papers4 papers in the last four weeks, down 20% on the four weeks before. 0.0% of all new papers.

  1. RS-WorldModel: a Unified Model for Remote Sensing Understanding and Future Sense Forecasting

    Mar 16, 2026Linrui Xu, Zhongan Wang, Fei Shen +4World Model LearningRemote Sensing VLMs

    Central South University · Zhejiang University · National University of Singapore +2

  2. UAV traffic scene understanding: A regulation embedded multi-modal network and a unified benchmark

    Mar 11, 2026Yu Zhang, Zhicheng Zhao, Ze Luo +2Remote Sensing VQAKnowledge-Based VQA

    Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China · University of Chinese Academy of Sciences, Beijing 100190, China · Anhui Provincial Key Laboratory of Multi-modal Cognitive Computation, Anhui University, Hefei 230601, China +1

  3. OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks

    Mar 10, 2026Ronghao Fu, Haoran Liu, Weijie Zhang +4VLM EvaluationRemote Sensing Benchmarks

    Jilin University, Changchun, China · Chang Guang Satellite Technology, Changchun, China

  4. Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing

    Mar 3, 2026Yi Liu, Jing Zhang, Di Wang +3Remote Sensing VQAVLM Hallucination Mitigation

    School of Computer Science, Wuhan University, China · Zhongguancun Academy, China · School of Computer Science, Chongqing University, China

  5. EarthSpatialBench: Benchmarking Spatial Reasoning Capabilities of Multimodal LLMs on Earth Imagery

    Feb 17, 2026Zelin Xu, Yupu Zhang, Saugat Adhikari +6Spatial Reasoning BenchmarksGeospatial Reasoning Benchmarks

    Department of Computer & Information Science & Engineering, University of Florida, Gainesville, FL, USA · Department of Computer Science, Indiana University Bloomington, Bloomington, IN, USA.

  6. SQuID: A Benchmark for Quantitative Spatial Reasoning on Satellite Imagery

    Jan 19, 2026Peter A. Massih, Eric Cosatto, Martin Renqiang MinSpatial Reasoning BenchmarksGeospatial Reasoning Benchmarks

    Department of Machine Learning, NEC Laboratories America · EPFL