Recursive Inception Network for Super-Resolution

In this paper, we propose a novel network for super-resolution and achieve the state-of-the-art performance with limited parameters. Inspired by the previous methods, we use ResNet to learn the residual part of the input patches. In addition, we introduce an inception-like structure that helps to extract features and a weight sharing mechanism is utilized among these inception blocks. By cascading multi-scale filters with separate paths in a deep network, the proposed method can fully exploit the contextual information over large image regions. Besides, the residual learning module makes the training phase easy to converge. Extensive experiments demonstrate that the proposed method can achieve the same performance with fewer parameters compared with the previous state-of-the-art methods.