Kernel Adversarial Learning for Real-world Image Super-resolution

TL;DR

This paper introduces a Kernel Adversarial Learning framework for real-world image super-resolution that adaptively models complex degradation processes, improving reconstruction accuracy over traditional methods.

Contribution

The paper presents a novel KASR framework that models realistic degradation kernels and noises adaptively, along with a high-frequency selective objective and iterative supervision.

Findings

Effective on real-world datasets

Outperforms existing super-resolution methods

Improves reconstruction accuracy

Abstract

Current deep image super-resolution (SR) approaches aim to restore high-resolution images from down-sampled images or by assuming degradation from simple Gaussian kernels and additive noises. However, these techniques only assume crude approximations of the real-world image degradation process, which should involve complex kernels and noise patterns that are difficult to model using simple assumptions. In this paper, we propose a more realistic process to synthesise low-resolution images for real-world image SR by introducing a new Kernel Adversarial Learning Super-resolution (KASR) framework. In the proposed framework, degradation kernels and noises are adaptively modelled rather than explicitly specified. Moreover, we also propose a high-frequency selective objective and an iterative supervision process to further boost the model SR reconstruction accuracy. Extensive experiments validate the effectiveness of the proposed framework on real-world datasets.