Contrastive Local Manifold Learning for No-Reference Image Quality Assessment

TL;DR

This paper introduces LML-IQA, a novel no-reference image quality assessment method that uses local manifold and contrastive learning to better capture perceptual quality, showing significant improvements over existing methods.

Contribution

The paper proposes a new NR-IQA approach combining local manifold learning and contrastive learning, with a mutual learning strategy for enhanced perceptual region recognition.

Findings

Achieved a PLCC of 0.942 on TID2013, outperforming previous methods.

Achieved a PLCC of 0.977 on CSIQ, surpassing state-of-the-art performance.

Demonstrated significant performance improvements across eight benchmark datasets.

Abstract

Image Quality Assessment (IQA) methods typically overlook local manifold structures, leading to compromised discriminative capabilities in perceptual quality evaluation. To address this limitation, we present LML-IQA, an innovative no-reference IQA (NR-IQA) approach that leverages a combination of local manifold learning and contrastive learning. Our approach first extracts multiple patches from each image and identifies the most visually salient region. This salient patch serves as a positive sample for contrastive learning, while other patches from the same image are treated as intra-class negatives to preserve local distinctiveness. Patches from different images also act as inter-class negatives to enhance feature separation. Additionally, we introduce a mutual learning strategy to improve the model's ability to recognize and prioritize visually important regions. Comprehensive experiments across eight benchmark datasets demonstrate significant performance gains over state-of-the-art methods, achieving a PLCC of 0.942 on TID2013 (compared to 0.908) and 0.977 on CSIQ (compared to 0.965).