Enhancing image quality prediction with self-supervised visual masking

Eurographics 2024

Uğur Çoğalan1     Mojtaba Bemana1     Hans-Peter Seidel1     Karol Myszkowski1    

1 MPI Informatik

Abstract

Full-reference image quality metrics (FR-IQMs) aim to measure the visual differences between a pair of reference and distorted images, with the goal of accurately predicting human judgments. However, existing FR-IQMs, including traditional ones like PSNR and SSIM and even perceptual ones such as HDR-VDP, LPIPS, and DISTS, still fall short in capturing the complexities and nuances of human perception. In this work, rather than devising a novel IQM model, we seek to improve upon the perceptual quality of existing FR-IQM methods. We achieve this by considering visual masking, an important characteristic of the human visual system that changes its sensitivity to distortions as a function of local image content. Specifically, for a given FR-IQM metric, we propose to predict a visual masking model that modulates reference and distorted images in a way that penalizes the visual errors based on their visibility. Since the ground truth visual masks are difficult to obtain, we demonstrate how they can be derived in a self-supervised manner solely based on mean opinion scores (MOS) collected from an FR-IQM dataset. Our approach results in enhanced FR-IQM metrics that are more in line with human prediction both visually and quantitatively.



Interactive Comparisons

Dataset

Scene

Metric



Please click Distorted image to switch between reference!

Distorted image

Reference image

Original

Enhanced





Citation and Materials

Uğur Çoğalan, Mojtaba Bemana, Hans-Peter Seidel, Karol Myszkowski
Enhancing image quality prediction with self-supervised visual masking
Computer Graphics Forum (Proc. EuroGraphics 2024)

@misc{çoğalan2024enhancing,
title={Enhancing image quality prediction with self-supervised visual masking}, 
author={Uğur Çoğalan and Mojtaba Bemana and Hans-Peter Seidel and Karol Myszkowski},
year={2024},
eprint={2305.19858},
archivePrefix={arXiv},
primaryClass={cs.CV}}.

Paper (Full Author's Copy)
			
Github Source Code!
						
				


Imprint / Data Protection