CARN: Convolutional Anchored Regression Network for Fast and Accurate Single Image Super-Resolution

Yawei Li, Eirikur Agustsson, Shuhang Gu, Radu Timofte, Luc Van Gool

Abstract: Although the accuracy of super-resolution (SR) methods based on convolutional neural networks (CNN) soars high, the complexity and computation also explode with the increased depth and width of the network. Thus, we propose the convolutional anchored regression network (CARN) for fast and accurate single image super-resolution (SISR). Inspired by locally linear regression methods (A+ and ARN), the new architecture consists of regression blocks that map input features from one feature space to another. Different from A+ and ARN, CARN is no longer relying on or limited by hand-crafted features. Instead, it is an end-to-end design where all the operations are converted to convolutions so that the key concepts, i.e., features, anchors, and regressors, are learned jointly. The experiments show that CARN achieves the best speed and accuracy trade-off among the SR methods. The code is available at https://github.com/ofsoundof/CARN .