mlsanityData to 14 Oct 2026

Reference-Free Image Quality Metric for Degradation and Reconstruction Artifacts

arXiv 2405.02208 ↗First posted 1 May 2024eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 34 references that are in the map. First posted on arXiv 1 May 2024.

Builds on

21 of 34 references.

References · 21

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  4. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  5. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  6. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  7. 2016Colorful Image Colorizationcited by 1,114
  8. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  9. 2018Object Detection with Deep Learning: A Reviewcited by 528
  10. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 470
  11. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 387
  12. 2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 178
9 more
  1. 2018PieAPP: Perceptual Image-Error Assessment through Pairwise Preferencecited by 160
  2. 2019Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchycited by 156
  3. 2015Compression Artifacts Reduction by a Deep Convolutional Networkcited by 136
  4. 2020A Survey on Instance Segmentation: State of the artcited by 85
  5. 2016Medical image denoising using convolutional denoising autoencoderscited by 76
  6. 2016Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connectionscited by 30
  7. 2017ADMM-Net: A Deep Learning Approach for Compressive Sensing MRIcited by 28
  8. 2014Jpeg Image Compression Using Discrete Cosine Transform - A Surveycited by 11
  9. 2018PDNet: Semantic Segmentation integrated with a Primal-Dual Network for Document binarizationcited by 2

Built on by

Not cited yet.