arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.09874cs.CVcs.LGq-bio.NC
收藏

图像统计预测感知质量指标的敏感性

Image Statistics Predict the Sensitivity of Perceptual Quality Metrics

School of Engineering Mathematics and Technology, University of Bristol(布里斯托大学工程数学与技术学院);Image Processing Lab, Universitat de Valencia(瓦伦西亚大学图像处理实验室)

Alexander Hepburn, Valero Laparra, Raúl Santos-Rodriguez, Jesús Malo

AI总结:

本文利用自然图像生成模型直接估计图像概率,提出仅含两个概率相关因素的简单回归模型,以预测主观图像质量指标敏感性,并通过观察者实验和经典心理物理趋势验证。

摘要:

此前,Barlow 和 Attneave 假设生物视觉与信息最大化之间存在联系。遵循 Shannon 的理论,信息利用自然图像的概率来定义。若干生理和心理物理现象已从 info-max、高效编码或最优去噪等原理中推导出来。然而,目前尚不清楚这种联系如何用源自图像概率的数学术语来表达。经典推导受到关于概率模型和传感器行为的强假设制约。此外,经典图像模型无法给出准确的概率估计,这限制了对该假设的直接评估。本文中,我们使用自然图像生成模型直接评估图像概率,并分析与概率相关的因素如何组合,以预测最先进的主观图像质量指标(作为人类感知的代理)的敏感性。我们利用信息论和回归分析找到了一个简单模型,该模型仅结合两个与概率相关的因素,便与主观指标达到 0.77 的相关性。这种基于概率的模型通过两种方式得到验证:在主观质量实验中与真实观察者的意见直接比较,以及复现经典心理物理事实的基本趋势,例如 Contrast Sensitivity Function(对比敏感度函数)、Weber 定律和对比掩蔽。

英文摘要:

Previously, Barlow and Attneave hypothesised a link between biological vision and information maximisation. Following Shannon, information was defined using the probability of natural images. Several physiological and psychophysical phenomena have been derived from principles like info-max, efficient coding, or optimal denoising. However, it remains unclear how this link is expressed in mathematical terms from image probability. Classical derivations were subjected to strong assumptions on the probability models and on the behaviour of the sensors. Moreover, the direct evaluation of the hypothesis was limited by the inability of classical image models to deliver accurate estimates of the probability. Here, we directly evaluate image probabilities using a generative model for natural images, and analyse how probability-related factors can be combined to predict the sensitivity of state-of-the-art subjective image quality metrics, a proxy for human perception. We use information theory and regression analysis to find a simple model that when combining just two probability-related factors achieves 0.77 correlation with subjective metrics. This probability-based model is validated in two ways: through direct comparison with the opinion of real observers in a subjective quality experiment, and by reproducing basic trends of classical psychophysical facts such as the Contrast Sensitivity Function, the Weber-law, and contrast masking.

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。

↑