Toward Real-World Single Image Super-Resolution: A New Benchmark and a New Model

• Published in: Proceedings / IEEE International Conference on Computer Vision pp. 3086 - 3095
• Main Authors: Cai, Jianrui, Zeng, Hui, Yong, Hongwei, Cao, Zisheng, Zhang, Lei
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2019
• Subjects: Benchmark testing; Cameras; Degradation; Image resolution; Kernel; Lenses; Training

Most of the existing learning-based single image super-resolution (SISR) methods are trained and evaluated on simulated datasets, where the low-resolution (LR) images are generated by applying a simple and uniform degradation (i.e., bicubic downsampling) to their high-resolution (HR) counterparts. H...