DeepAI AI Chat
Log In Sign Up

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution

by   Kai Zhang, et al.
ETH Zurich

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 ESRGAN 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.


page 5

page 6

page 7

page 8


Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels

While deep neural networks (DNN) based single image super-resolution (SI...

Fast and Robust Cascade Model for Multiple Degradation Single Image Super-Resolution

Single Image Super-Resolution (SISR) is one of the low-level computer vi...

Learning a Single Convolutional Super-Resolution Network for Multiple Degradations

Recent years have witnessed the unprecedented success of deep convolutio...

Unsupervised Single Image Super-resolution Under Complex Noise

While the researches on single image super-resolution (SISR), especially...

Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradations

Deep Convolutional Neural Networks (CNNs) have achieved remarkable resul...

Blind Image Super-Resolution: A Survey and Beyond

Blind image super-resolution (SR), aiming to super-resolve low-resolutio...

Deep Unfolding Network for Image Super-Resolution

Learning-based single image super-resolution (SISR) methods are continuo...

Code Repositories


Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021) (PyTorch) - We released the testing code!

view repo