Reference-Free Image Quality Metric for Degradation and Reconstruction Artifacts
Preprint
Abstract
Image Quality Assessment (IQA) is essential in various Computer Vision tasks such as image deblurring and super-resolution. However, most IQA methods require reference images, which are not always available. While there are some reference-free IQA metrics, they have limitations in simulating human perception and discerning subtle image quality variations. We hypothesize that the JPEG quality factor is representatives of image quality measurement, and a well-trained neural network can learn to accurately evaluate image quality without requiring a clean reference, as it can recognize image degradation artifacts based on prior knowledge. Thus, we developed a reference-free quality evaluation network, dubbed "Quality Factor (QF) Predictor", which does not require any reference. Our QF Predictor is a lightweight, fully convolutional network comprising seven layers. The model is trained in a self-supervised manner: it receives JPEG compressed image patch with a random QF as input, is trained to accurately predict the corresponding QF. We demonstrate the versatility of the model by applying it to various tasks. First, our QF Predictor can generalize to measure the severity of various image artifacts, such as Gaussian Blur and Gaussian noise. Second, we show that the QF Predictor can be trained to predict the undersampling rate of images reconstructed from Magnetic Resonance Imaging (MRI) data.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- SwinIR: Image Restoration Using Swin Transformer2021
- MoDL: Model-Based Deep Learning Architecture for Inverse ProblemsIEEE Transactions on Medical Imaging, 2018
- DeepSim: Deep similarity for image quality assessmentNeurocomputing, 2017
- Medical Image Denoising Using Convolutional Denoising Autoencoders2016
- Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles2016
- Colorful Image Colorization2016
- Compression Artifacts Reduction by a Deep Convolutional Network2015
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Image Super-Resolution Using Deep Convolutional NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Structural Approaches to Image Quality Assessment2005