Blind image super-resolution based on prior correction network

Abstract Convolutional neural networks (CNNs) based super-resolution (SR) methods have achieved remarkable progress in recent years. Most of these methods assume that the degradation is known and fixed, such as bicubic downsampling. However, the performance of CNNs-based methods suffers from a severe drop when the actual degradation mismatch the training one. This paper proposes a prior correction network (PCNet) to solve the blind SR problem, which makes CNNs-based super-resolvers trained in a fixed blur kernel but applied to other unknown blur kernels. The PCNet consists of a kernel estimation network, a correction filter module, and a correction refinement network. The kernel estimation network aims to estimate unknown blur kernel from the input low-resolution (LR) image. The correction filter module then transfers the estimated degraded domains to adapt to specific degradations (e.g., bicubic downsampling). Finally, the correction refinement network adjusts the corrected LR image to eliminate the influence of blur kernel mismatch or misestimate. Experimental results on diverse datasets show that the proposed PCNet, combined with existing CNNs-based SR methods, outperforms other state-of-the-art algorithms for blind SR. Code is available at: \url{ https://github.com/caoxiang104/PCNet }.