Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment

Abstract

We present a deep neural network-based approach to image quality assessment (IQA). The network is trained end-to-end and comprises ten convolutional layers and five pooling layers for feature extraction, and two fully connected layers for regression, which makes it significantly deeper than related IQA models. Unique features of the proposed architecture are that: 1) with slight adaptations it can be used in a no-reference (NR) as well as in a full-reference (FR) IQA setting and 2) it allows for joint learning of local quality and local weights, i.e., relative importance of local quality to the global quality estimate, in an unified framework. Our approach is purely data-driven and does not rely on hand-crafted features or other types of prior domain knowledge about the human visual system or image statistics. We evaluate the proposed approach on the LIVE, CISQ, and TID2013 databases as well as the LIVE In the wild image quality challenge database and show superior performance to state-of-the-art NR and FR IQA methods. Finally, cross-database evaluation shows a high ability to generalize between different databases, indicating a high robustness of the learned features.

References in corpus (1)

• Massive Online Crowdsourced Study of Subjective and Objective Picture Quality

Cited by in corpus (39)

• Image Quality Assessment: Unifying Structure and Texture Similarity
• Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
• Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild
• Image Quality Assessment using Contrastive Learning
• DeepISP: Towards Learning an End-to-End Image Processing Pipeline
• Comparison of Image Quality Models for Optimization of Image Processing Systems
• GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment
• Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Training
• Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessment
• Confusing Image Quality Assessment: Towards Better Augmented Reality Experience
• A Perceptually Weighted Rank Correlation Indicator for Objective Image Quality Assessment
• ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression
• Locally Adaptive Structure and Texture Similarity for Image Quality Assessment
• No-reference Screen Content Image Quality Assessment with Unsupervised Domain Adaptation
• No-Reference Image Quality Assessment by Hallucinating Pristine Features
• Multi-pooled Inception features for no-reference image quality assessment
• Artifact- and content-specific quality assessment for MRI with image rulers
• Bilevel methods for image reconstruction
• SUR-FeatNet: Predicting the Satisfied User Ratio Curvefor Image Compression with Deep Feature Learning
• Quality Evaluation of Arbitrary Style Transfer: Subjective Study and Objective Metric
• PIQI: Perceptual Image Quality Index based on Ensemble of Gaussian Process Regression
• Gap-closing Matters: Perceptual Quality Evaluation and Optimization of Low-Light Image Enhancement
• Deep Ensembling for Perceptual Image Quality Assessment
• Real-Time Quality Assessment of Pediatric MRI via Semi-Supervised Deep Nonlocal Residual Neural Networks
• RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training
• Light Field Synthesis by Training Deep Network in the Refocused Image Domain
• Evaluation of quality measures for color quantization
• (ASNA) An Attention-based Siamese-Difference Neural Network with Surrogate Ranking Loss function for Perceptual Image Quality Assessment
• PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance
• Full-Reference Speech Quality Estimation with Attentional Siamese Neural Networks
• Bias-Aware Loss for Training Image and Speech Quality Prediction Models from Multiple Datasets
• MS-SCANet: A Multiscale Transformer-Based Architecture with Dual Attention for No-Reference Image Quality Assessment
• A Comprehensive Review of Deep Learning-based Single Image Super-resolution
• BVI-VFI: A Video Quality Database for Video Frame Interpolation
• A combined full-reference image quality assessment approach based on convolutional activation maps
• Annotation-Free Human Sketch Quality Assessment
• RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment
• Evaluating the Stability of Deep Image Quality Assessment With Respect to Image Scaling
• IG-FIQA: Improving Face Image Quality Assessment through Intra-class Variance Guidance robust to Inaccurate Pseudo-Labels