SenseBench: 一个用于遥感低级视觉感知与描述的大型视觉-语言模型基准
SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models
AI总结：
本文提出SenseBench，首个专为遥感低级视觉感知与描述设计的基准，通过物理基础的分层分类体系，评估29种先进VLMs在遥感降质识别中的性能，揭示领域先验偏差、多退化崩溃、流畅性幻觉及感知-描述反转效应。
摘要：
低级视觉感知是可靠遥感（RS）图像分析的基础，但当前图像质量评估（IQA）方法输出不可解释的标量分数而非描述物理驱动的遥感退化，与RS专家的诊断需求存在显著偏差。虽然视觉-语言模型（VLMs）通过提供语言引导的IQA成为替代方案，但其视觉先验严重偏向地面级自然图像。因此，VLMs能否克服这一领域差距以感知和描述遥感退化仍缺乏充分研究。为此，我们提出SenseBench，首个专为遥感低级视觉感知与描述设计的诊断基准。该基准由基于物理的分层分类体系驱动，统一了非参考和参考基于的范式，包含超过10,000个精心挑选的实例，覆盖6种主要和22种细粒度的遥感退化类别。具体而言，设计了两种互补的评估协议：客观低级视觉感知和主观诊断描述。对29种最先进的VLMs的全面评估揭示了领域先验偏差、多退化崩溃、流畅性幻觉及感知-描述反转效应。我们希望SenseBench能提供一个稳健的评估测试平台和高质量的诊断数据，推动VLMs在遥感低级感知中的发展。代码和数据集可在此获取：https://github.com/Zhong-Chenchen/SenseBench
英文摘要：
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}}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
