Research on image Super-resolution based on Compact Multi-path Convolution Neural Network

In order to improve the resolution degradation problem of static image and reduce network parameters, a compact multi-path convolution neural network based image super-resolution algorithm is proposed in this paper. This multi-path structure model is adopted to make full use of low-resolution image information, and we use a residual learning strategy to learn residual information between the low level and high level images to reconstruct images super-resolution. Nevertheless, networks with ReLU tend to perform poorly when the number of filter parameters is constrained to a small number. To enhance network generalization ability and make the network more compact, the activated the function named Max-feature-Max is adopted here. Experimental results show that the proposed method has good reconstruction ability with image clarity and edge sharpness and has better super-resolution perform in the both objective evaluation and subjective visual effect. This method lays a theoretical foundation for portable high-performance super-resolution reconstruction.