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

TL;DR

This paper introduces a complex, realistic degradation model for training deep blind super-resolution models, significantly improving their performance on diverse real-world degraded images.

Contribution

The paper proposes a new, more comprehensive degradation model combining various blur, downsampling, and noise factors for better real-world super-resolution training.

Findings

Deep blind ESRGAN trained with the new model outperforms previous methods on synthetic and real images.

The model enhances super-resolution performance across diverse degradations.

Experimental results confirm improved practicability of deep super-resolvers.

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 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.