From Distance to Dependency: A Paradigm Shift of Full-reference Image Quality Assessment

11/09/2022
by   Hanwei Zhu, et al.
0

Deep learning-based full-reference image quality assessment (FR-IQA) models typically rely on the feature distance between the reference and distorted images. However, the underlying assumption of these models that the distance in the deep feature domain could quantify the quality degradation does not scientifically align with the invariant texture perception, especially when the images are generated artificially by neural networks. In this paper, we bring a radical shift in inferring the quality with learned features and propose the Deep Image Dependency (DID) based FR-IQA model. The feature dependency facilitates the comparisons of deep learning features in a high-order manner with Brownian distance covariance, which is characterized by the joint distribution of the features from reference and test images, as well as their marginal distributions. This enables the quantification of the feature dependency against nonlinear transformation, which is far beyond the computation of the numerical errors in the feature space. Experiments on image quality prediction, texture image similarity, and geometric invariance validate the superior performance of our proposed measure.

READ FULL TEXT

page 2

page 7

research
08/09/2021

No-Reference Image Quality Assessment by Hallucinating Pristine Features

In this paper, we propose a no-reference (NR) image quality assessment (...
research
02/22/2023

Debiased Mapping for Full-Reference Image Quality Assessment

Mapping images to deep feature space for comparisons has been wildly ado...
research
08/05/2022

DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space

Existing deep learning-based full-reference IQA (FR-IQA) models usually ...
research
05/24/2019

Perception Evaluation -- A new solar image quality metric based on the multi-fractal property of texture features

Next-generation ground-based solar observations require good image quali...
research
12/08/2014

Image quality assessment measure based on natural image statistics in the Tetrolet domain

This paper deals with a reduced reference (RR) image quality measure bas...
research
04/16/2020

Image Quality Assessment: Unifying Structure and Texture Similarity

Objective measures of image quality generally operate by making local co...
research
03/04/2021

Perceptual Image Restoration with High-Quality Priori and Degradation Learning

Perceptual image restoration seeks for high-fidelity images that most li...

Please sign up or login with your details

Forgot password? Click here to reset