Noise-robust superresolution based on a classified dictionary

Conventional learning-based superresolution algorithms tend to boost noise components existing in input images because the algorithms are usually learned inanoise-free environment. Even thoughaspecific noise reduction algorithm is applied to noisy images prior to superresolution, visual quality degradation is inevitable due to the mismatch between noise-free images and denoised images. Accordingly, we presentanoise-robust superresolution algorithm that overcomes this problem. In the learning phase,adictionaryclassified according to noise level is constructed, and thenahigh-resolution image is synthesized using the dictionary in the inference phase. Experimental results show that the proposed algorithm outperforms existing algorithms for various noisy images.