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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiao, Kang, Wang, Xu, He, Yulin, Chen, Baoliang, Shen, Xuelin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929463571251200
author Xiao, Kang
Wang, Xu
He, Yulin
Chen, Baoliang
Shen, Xuelin
author_facet Xiao, Kang
Wang, Xu
He, Yulin
Chen, Baoliang
Shen, Xuelin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_09920
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment Enhancement
Xiao, Kang
Wang, Xu
He, Yulin
Chen, Baoliang
Shen, Xuelin
Computer Vision and Pattern Recognition
Multimedia
Image and Video Processing
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.
title Sliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment Enhancement
topic Computer Vision and Pattern Recognition
Multimedia
Image and Video Processing
url https://arxiv.org/abs/2408.09920