像素完美：基于空间感知失真的关系图像质量评估
摘要
传统图像质量评估（IQA）方法依赖于平均意见分数（MOS），其收集资源昂贵且无法提供针对特定图像失真的可解释、局部反馈。我们通过从绝对质量预测转向关系型和方向性评估来克服这些限制。 our approach utilizes a self-supervised synthetic distortion engine to generate training data, eliminating the need for manual annotation. A distortion prediction network is trained with an anti-symmetric objective to produce spatially-aware, disentangled maps that identify the type, intensity, and direction of distortions relative to a reference image. Subsequently, a scoring network is trained via contrastive learning on ordinally ranked image sets to predict a relational quality score. Our method provides a more granular and interpretable approach to IQA for the targeted optimization of image processing algorithms without requiring any human-labeled quality scores.
引用
@article{arxiv.2605.02863,
title = {Pixel Perfect: Relational Image Quality Assessment with Spatially-Aware Distortions},
author = {Fadeel Sher Khan and Long N. Le and Abhinau K. Venkataramanan and Seok-Jun Lee and Hamid R. Sheikh},
journal= {arXiv preprint arXiv:2605.02863},
year = {2026}
}