Sliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment Enhancement

TL;DR

This paper introduces a training-free attention estimation method using sliced maximal information coefficient to enhance existing image quality assessment models by better mimicking human visual perception.

Contribution

It proposes a novel, training-free attention estimation strategy that improves the performance of existing IQA models by modeling human visual attention through statistical dependency.

Findings

Enhanced IQA models show improved correlation with human perception.

The method generalizes well across different IQA measures.

Source code availability facilitates reproducibility.

Abstract

Full-reference image quality assessment (FR-IQA) models generally operate by measuring the visual differences between a degraded image and its reference. However, existing FR-IQA models including both the classical ones (eg, PSNR and SSIM) and deep-learning based measures (eg, LPIPS and DISTS) still exhibit limitations in capturing the full perception characteristics of the human visual system (HVS). In this paper, instead of designing a new FR-IQA measure, we aim to explore a generalized human visual attention estimation strategy to mimic the process of human quality rating and enhance existing IQA models. In particular, we model human attention generation by measuring the statistical dependency between the degraded image and the reference image. The dependency is captured in a training-free manner by our proposed sliced maximal information coefficient and exhibits surprising generalization in different IQA measures. Experimental results verify the performance of existing IQA models can be consistently improved when our attention module is incorporated. The source code is available at https://github.com/KANGX99/SMIC.