Sliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment Enhancement
Preprint
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.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Comparison of Full-Reference Image Quality Models for Optimization of Image Processing SystemsInternational Journal of Computer Vision, 2021
- Blind image quality assessment via learnable attention-based poolingPattern Recognition, 2019
- Deep Neural Networks for No-Reference and Full-Reference Image Quality AssessmentIEEE Transactions on Image Processing, 2017
- Image database TID2013: Peculiarities, results and perspectivesSignal Processing: Image Communication, 2015
- VSI: A Visual Saliency-Induced Index for Perceptual Image Quality AssessmentIEEE Transactions on Image Processing, 2014
- minerva and minepy: a C engine for the MINE suite and its R, Python and MATLAB wrappersBioinformatics, 2012
- Information Content Weighting for Perceptual Image Quality AssessmentIEEE Transactions on Image Processing, 2010
- Learning to predict where humans look2009
- Image information and visual qualityIEEE Transactions on Image Processing, 2006
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004