C3Net: A Cross-Channel Cross-Scale and Cross-Stage Network for Single Image Super-Resolution

Abstract

In this paper, we propose a cross-channel, cross-scale, and cross-stage network (C <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> Net) for single image super-resolution, which effectively shares the features learned from multiple channels, multiple scales, and multiple stages. Multi-scale spatial features are extracted in each stage in an encoder-decoder fashion. The channel attention is performed after each encoder to exploit the inter-channel dependencies. After that, we design a cross-stage and cross-scale feature sharing module to accelerate the feature sharing across different scales and different stages. The whole network is optimized by multiple similar stages to reduce the number of parameters. Finally, super-resolution images of multiple resolutions are reconstructed simultaneously. We evaluate the proposed network on four benchmark datasets by comparing it with eleven state-of-the-art methods. Comprehensive experiments show the proposed network outperforms state-of-the-art methods by fewer parameters. The source code is available at https://github.com/thinkerww/SR_Version.