MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors study two main ways to estimate how good an image looks without a reference: regression, which predicts exact quality scores, and ranking, which orders images by quality. They find that both methods actually work by learning about the differences in quality between images, called quality margins. Using this idea, the authors create a new approach called MR-IQA that directly optimizes these quality margins with reinforcement learning. Their method performs well on several tests and helps better understand how to model image quality.
Blind Image Quality AssessmentRegressionRankingQuality MarginPairwise Relational DistanceReinforcement LearningPolicy RewardPLCCSRCCImage Quality Metrics
Authors
Yuan Li, Youyuan Lin, Zitang Sun, Yung-Hao Yang, Kiyofumi Miyoshi, Chenhui Chu, Shin'ya Nishida
Abstract
Blind image quality assessment (BIQA) is commonly built on two basic learning paradigms: regression and ranking. Regression calibrates absolute scores, whereas ranking recovers quality structure from ordinal relations. Although joint regression-ranking supervision often improves BIQA, the relation between the two paradigms remains largely empirical and underexplored. In this work, we revisit what underlies regression and ranking and identify pairwise relational distance, termed quality margin, as their common bridge. Our derivation shows that, at the objective-optimization level, both paradigms fit quality margins: regression fits margins induced by score endpoints, while ranking fits transformed or sign-level margins through preference probabilities. Motivated by this insight, we propose MR-IQA, a direct quality-margin optimization framework for reinforcement learning (RL)-based BIQA. MR-IQA samples quality scores and optimizes pairwise margin errors as policy rewards, thereby modeling quality structure more explicitly. Experiments on six BIQA benchmarks show competitive general performance, and controlled comparisons demonstrate that MR-IQA achieves the strongest average PLCC/SRCC over regression- or ranking-based RL methods. Our findings provide a new insight into unifying regression and ranking, offering a theoretical basis for understanding quality-structure modeling in BIQA and beyond.