No-Reference Image Quality Assessment by Hallucinating Pristine Features

Abstract

In this paper, we propose a no-reference (NR) image quality assessment (IQA) method via feature level pseudo-reference (PR) hallucination. The proposed quality assessment framework is grounded on the prior models of natural image statistical behaviors and rooted in the view that the perceptually meaningful features could be well exploited to characterize the visual quality. Herein, the PR features from the distorted images are learned by a mutual learning scheme with the pristine reference as the supervision, and the discriminative characteristics of PR features are further ensured with the triplet constraints. Given a distorted image for quality inference, the feature level disentanglement is performed with an invertible neural layer for final quality prediction, leading to the PR and the corresponding distortion features for comparison. The effectiveness of our proposed method is demonstrated on four popular IQA databases, and superior performance on cross-database evaluation also reveals the high generalization capability of our method. The implementation of our method is publicly available on https://github.com/Baoliang93/FPR.

References in corpus (9)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• NICE: Non-linear Independent Components Estimation
• Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
• dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs
• Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training
• Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessment
• No-reference Screen Content Image Quality Assessment with Unsupervised Domain Adaptation
• Self-supervised Low Light Image Enhancement and Denoising
• Referenceless Rate-Distortion Modeling with Learning from Bitstream and Pixel Features