Kernel Adversarial Learning for Real-world Image Super-resolution
This addresses the challenge of realistic image degradation for applications in computer vision and image processing, representing an incremental improvement over existing methods.
The paper tackles the problem of real-world image super-resolution by proposing a Kernel Adversarial Learning framework to model complex degradation kernels and noises, achieving improved reconstruction accuracy as validated on real-world datasets.
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.