Patch orientation-specified network for learning-based image super-resolution

Abstract

Learning-based image super-resolution is considered as a promising solution to reconstruct a high-resolution image from a low-resolution image. To improve the super-resolution performance dramatically, this Letter focuses on the effect of training dataset on the performance and proposes an image super-resolution scheme based on patch orientation-specified network. In particular, a deep neural network is trained using patches with a specific orientation and angular transformation is combined with the neural network to cope with various orientations in input patches. Experimental results show the suggested network model is superior to existing state-of-the-art super-resolution alternatives.