Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network

Abstract

We propose a deep bilinear model for blind image quality assessment (BIQA) that handles both synthetic and authentic distortions. Our model consists of two convolutional neural networks (CNN), each of which specializes in one distortion scenario. For synthetic distortions, we pre-train a CNN to classify image distortion type and level, where we enjoy large-scale training data. For authentic distortions, we adopt a pre-trained CNN for image classification. The features from the two CNNs are pooled bilinearly into a unified representation for final quality prediction. We then fine-tune the entire model on target subject-rated databases using a variant of stochastic gradient descent. Extensive experiments demonstrate that the proposed model achieves superior performance on both synthetic and authentic databases. Furthermore, we verify the generalizability of our method on the Waterloo Exploration Database using the group maximum differentiation competition.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Two-Stream Convolutional Networks for Action Recognition in Videos
• Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment
• Massive Online Crowdsourced Study of Subjective and Objective Picture Quality
• MatConvNet - Convolutional Neural Networks for MATLAB
• dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs

Cited by in corpus (41)

• Internet of Underwater Things and Big Marine Data Analytics -- A Comprehensive Survey
• Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild
• Image Quality Assessment using Contrastive Learning
• 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
• Shadow Removal by a Lightness-Guided Network with Training on Unpaired Data
• UIF: An Objective Quality Assessment for Underwater Image Enhancement
• Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach
• No-reference Screen Content Image Quality Assessment with Unsupervised Domain Adaptation
• Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey
• No-Reference Image Quality Assessment by Hallucinating Pristine Features
• Multi-pooled Inception features for no-reference image quality assessment
• Large Multi-modality Model Assisted AI-Generated Image Quality Assessment
• Bilevel methods for image reconstruction
• Gap-closing Matters: Perceptual Quality Evaluation and Optimization of Low-Light Image Enhancement
• Deep Ensembling for Perceptual Image Quality Assessment
• MetaIQA: Deep Meta-learning for No-Reference 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
• MS-SCANet: A Multiscale Transformer-Based Architecture with Dual Attention for No-Reference Image Quality Assessment
• A Generalised Deep Meta-Learning Model for Automated Quality Control of Cardiovascular Magnetic Resonance Images
• Blind Omnidirectional Image Quality Assessment with Viewport Oriented Graph Convolutional Networks
• Learning to Blindly Assess Image Quality in the Laboratory and Wild
• A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis
• Deep Neural Networks for Blind Image Quality Assessment: Addressing the Data Challenge
• No-Reference Quality Assessment for 360-degree Images by Analysis of Multi-frequency Information and Local-global Naturalness
• Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment
• 3D Face Anti-spoofing with Factorized Bilinear Coding
• Blind Image Quality Assessment for MRI with A Deep Three-dimensional content-adaptive Hyper-Network
• Annotation-Free Human Sketch Quality Assessment
• Troubleshooting Blind Image Quality Models in the Wild
• Subjective and Objective De-raining Quality Assessment Towards Authentic Rain Image
• Learning from Synthetic Data for Opinion-free Blind Image Quality Assessment in the Wild
• MUSIQ: Multi-scale Image Quality Transformer
• ER-IQA: Boosting Perceptual Quality Assessment Using External Reference Images
• Learning Generalized Spatial-Temporal Deep Feature Representation for No-Reference Video Quality Assessment
• Blind Quality Assessment for Image Superresolution Using Deep Two-Stream Convolutional Networks
• D-Judge: How Far Are We? Assessing the Discrepancies Between AI-synthesized and Natural Images through Multimodal Guidance
• Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment
• Related Work on Image Quality Assessment
• MMP-2K: A Benchmark Multi-Labeled Macro Photography Image Quality Assessment Database