dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs

Abstract

Objective assessment of image quality is fundamentally important in many image processing tasks. In this work, we focus on learning blind image quality assessment (BIQA) models which predict the quality of a digital image with no access to its original pristine-quality counterpart as reference. One of the biggest challenges in learning BIQA models is the conflict between the gigantic image space (which is in the dimension of the number of image pixels) and the extremely limited reliable ground truth data for training. Such data are typically collected via subjective testing, which is cumbersome, slow, and expensive. Here we first show that a vast amount of reliable training data in the form of quality-discriminable image pairs (DIP) can be obtained automatically at low cost by exploiting large-scale databases with diverse image content. We then learn an opinion-unaware BIQA (OU-BIQA, meaning that no subjective opinions are used for training) model using RankNet, a pairwise learning-to-rank (L2R) algorithm, from millions of DIPs, each associated with a perceptual uncertainty level, leading to a DIP inferred quality (dipIQ) index. Extensive experiments on four benchmark IQA databases demonstrate that dipIQ outperforms state-of-the-art OU-BIQA models. The robustness of dipIQ is also significantly improved as confirmed by the group MAximum Differentiation (gMAD) competition method. Furthermore, we extend the proposed framework by learning models with ListNet (a listwise L2R algorithm) on quality-discriminable image lists (DIL). The resulting DIL Inferred Quality (dilIQ) index achieves an additional performance gain.

References in corpus (1)

• Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index

Cited by in corpus (18)

• Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
• Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild
• Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
• Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Training
• Diffusion Models, Image Super-Resolution And Everything: A Survey
• A Perceptually Weighted Rank Correlation Indicator for Objective Image Quality Assessment
• Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
• No-reference Screen Content Image Quality Assessment with Unsupervised Domain Adaptation
• No-Reference Image Quality Assessment by Hallucinating Pristine Features
• Artifact- and content-specific quality assessment for MRI with image rulers
• PIQI: Perceptual Image Quality Index based on Ensemble of Gaussian Process Regression
• Deep Ensembling for Perceptual Image Quality Assessment
• Intrinsic Image Popularity Assessment
• RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training
• A Comprehensive Review of Deep Learning-based Single Image Super-resolution
• Characterizing Generalized Rate-Distortion Performance of Video Coding: An Eigen Analysis Approach
• Annotation-Free Human Sketch Quality Assessment
• No-reference geometry quality assessment for colorless point clouds via list-wise rank learning