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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhong, Chen, An, Xiao, Sun, Jiaxing, Gui, Zihan, Yang, Guangyi, He, Wei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916000854704128
author Zhong, Chen
An, Xiao
Sun, Jiaxing
Gui, Zihan
Yang, Guangyi
He, Wei
author_facet Zhong, Chen
An, Xiao
Sun, Jiaxing
Gui, Zihan
Yang, Guangyi
He, Wei
contents 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}}.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10576
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models
Zhong, Chen
An, Xiao
Sun, Jiaxing
Gui, Zihan
Yang, Guangyi
He, Wei
Computer Vision and Pattern Recognition
Artificial Intelligence
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}}.
title SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.10576