SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models

TL;DR

SenseBench is a new benchmark designed to evaluate and improve vision-language models' ability to perceive and describe low-level visual degradations in remote sensing images, addressing domain gaps and diagnostic needs.

Contribution

It introduces the first dedicated diagnostic benchmark for remote sensing low-level perception, with a physics-based taxonomy and comprehensive evaluation protocols.

Findings

29 state-of-the-art VLMs show domain bias and perception issues.

SenseBench reveals phenomena like fluency illusion and perception-description inversion.

Benchmark facilitates advancing VLM development for remote sensing applications.

Abstract

Low-level visual perception underpins reliable remote sensing (RS) image analysis, yet current image quality assessment (IQA) methods output uninterpretable scalar scores rather than characterizing physics-driven RS degradations, deviating markedly from the diagnostic needs of RS experts. While Vision-Language Models (VLMs) present a compelling alternative by delivering language-grounded IQA, their visual priors are heavily biased toward ground-level natural images. Consequently, whether VLMs can overcome this domain gap to perceive and articulate RS artifacts remains insufficiently studied. To bridge this gap, we propose \textbf{SenseBench}, the first dedicated diagnostic benchmark for RS low-level visual perception and description. Driven by a physics-based hierarchical taxonomy that unifies both non-reference and reference-based paradigms, SenseBench features over 10K meticulously curated instances across 6 major and 22 fine-grained RS degradation categories. Specifically, two complementary protocols are designed for evaluation: objective low-level visual \textit{perception} and subjective diagnostic \textit{description}. Comprehensive evaluation of 29 state-of-the-art VLMs reveals not only skewed domain priors and multi-distortion collapse, but also \textit{fluency illusion} and a \textit{perception-description inversion} effect. We hope SenseBench provides a robust evaluation testbed and high-quality diagnostic data to advance the development of VLMs in RS low-level perception. Code and datasets are available \href{https://github.com/Zhong-Chenchen/SenseBench}{\textcolor{blue}{here}}.