Deep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradations

Rao Muhammad Umer, Gian Luca Foresti, Christian Micheloni
2019 Proceedings of the 13th International Conference on Distributed Smart Cameras - ICDSC 2019  
Single Image Super-Resolution (SISR) aims to generate a high-resolution (HR) image of a given low-resolution (LR) image. The most of existing convolutional neural network (CNN) based SISR methods usually take an assumption that a LR image is only bicubicly down-sampled version of an HR image. However, the true degradation (i.e. the LR image is a bicubicly downsampled, blurred and noisy version of an HR image) of a LR image goes beyond the widely used bicubic assumption, which makes the SISR
more » ... lem highly ill-posed nature of inverse problems. To address this issue, we propose a deep SISR network that works for blur kernels of different sizes, and different noise levels in an unified residual CNN-based denoiser network, which significantly improves a practical CNN-based super-resolver for real applications. Extensive experimental results on synthetic LR datasets and real images demonstrate that our proposed method not only can produce better results on more realistic degradation but also computational efficient to practical SISR applications.
doi:10.1145/3349801.3349823 dblp:conf/icdsc/UmerFM19 fatcat:ldi2ejxh35ahpa5vdzwmdyrqae