Saved in:
Bibliographic Details
Main Authors: Su, Shaolin, Rocafort, Josep M., Xue, Danna, Serrano-Lozano, David, Sun, Lei, Vazquez-Corral, Javier
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.13074
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918402428239872
author Su, Shaolin
Rocafort, Josep M.
Xue, Danna
Serrano-Lozano, David
Sun, Lei
Vazquez-Corral, Javier
author_facet Su, Shaolin
Rocafort, Josep M.
Xue, Danna
Serrano-Lozano, David
Sun, Lei
Vazquez-Corral, Javier
contents As super-resolution (SR) techniques advance, we observe a growing distrust of evaluation metrics in recent SR research. An inconsistency often emerges between certain evaluation criteria and human perceptual preference. Although current SR research employs varying metrics to evaluate SR performance, it remains underexplored how robust and reliable these metrics actually are. To bridge this gap, we conduct a comprehensive analysis of widely used image quality metrics, examining their consistency with human perception when evaluating state-of-the-art SR models. We show that some metrics exhibit only limited-or even negative-correlation with human preferences. We further identify several intrinsic challenges in SR evaluation that compromise the effectiveness of both full-reference (FR) and no-reference (NR) image quality assessment (IQA) frameworks. To address these issues, we propose a simple yet effective Relative Quality Index (RQI) framework, which assesses the relative quality discrepancy between image pairs. Our framework enables easy integration and notable improvements for existing IQA metrics in SR evaluation. Moreover, it can be utilized as a valuable training guide for SR models, enabling the generation of images with more realistic details while maintaining structural fidelity.
format Preprint
id arxiv_https___arxiv_org_abs_2503_13074
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bridging the Perception Gap in Image Super-Resolution Evaluation
Su, Shaolin
Rocafort, Josep M.
Xue, Danna
Serrano-Lozano, David
Sun, Lei
Vazquez-Corral, Javier
Computer Vision and Pattern Recognition
As super-resolution (SR) techniques advance, we observe a growing distrust of evaluation metrics in recent SR research. An inconsistency often emerges between certain evaluation criteria and human perceptual preference. Although current SR research employs varying metrics to evaluate SR performance, it remains underexplored how robust and reliable these metrics actually are. To bridge this gap, we conduct a comprehensive analysis of widely used image quality metrics, examining their consistency with human perception when evaluating state-of-the-art SR models. We show that some metrics exhibit only limited-or even negative-correlation with human preferences. We further identify several intrinsic challenges in SR evaluation that compromise the effectiveness of both full-reference (FR) and no-reference (NR) image quality assessment (IQA) frameworks. To address these issues, we propose a simple yet effective Relative Quality Index (RQI) framework, which assesses the relative quality discrepancy between image pairs. Our framework enables easy integration and notable improvements for existing IQA metrics in SR evaluation. Moreover, it can be utilized as a valuable training guide for SR models, enabling the generation of images with more realistic details while maintaining structural fidelity.
title Bridging the Perception Gap in Image Super-Resolution Evaluation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.13074