Designing a Practical Degradation Model for Deep Blind Image Super-Resolution
Authors:
Top Cited Papers
- 1 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4771-4780
Abstract
It is widely acknowledged that single image super-resolution (SISR) methods would not perform well if the assumed degradation model deviates from those in real images. Although several degradation models take additional factors into consideration, such as blur, they are still not effective enough to cover the diverse degradations of real images. To address this issue, this paper proposes to design a more complex but practical degradation model that consists of randomly shuffled blur, downsampling and noise degradations. Specifically, the blur is approximated by two convolutions with isotropic and anisotropic Gaussian kernels; the downsampling is randomly chosen from nearest, bilinear and bicubic interpolations; the noise is synthesized by adding Gaussian noise with different noise levels, adopting JPEG compression with different quality factors, and generating processed camera sensor noise via reverse-forward camera image signal processing (ISP) pipeline model and RAW image noise model. To verify the effectiveness of the new degradation model, we have trained a deep blind ES-RGAN super-resolver and then applied it to super-resolve both synthetic and real images with diverse degradations. The experimental results demonstrate that the new degradation model can help to significantly improve the practicability of deep super-resolvers, thus providing a powerful alternative solution for real SISR applications.Keywords
This publication has 49 references indexed in Scilit:
- Conditioned Regression Models for Non-blind Single Image Super-Resolution2015
- Revisiting Single Image Super-Resolution Under Internet Environment: Blur Kernels and Reconstruction Algorithms2015
- A Statistical Prediction Model Based on Sparse Representations for Single Image Super-ResolutionIEEE Transactions on Image Processing, 2014
- Accurate Blur Models vs. Image Priors in Single Image Super-resolution2013
- Nonparametric Blind Super-resolution2013
- On Bayesian Adaptive Video Super ResolutionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Gaussian Assumption: The Least Favorable but the Most Useful [Lecture Notes]IEEE Signal Processing Magazine, 2013
- Nonlocally Centralized Sparse Representation for Image RestorationIEEE Transactions on Image Processing, 2012
- What is the space of camera response functions?2003
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002