Reviews: Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution

Summary: This paper proposes a CNN architecture called SRCliqueNet for single-image super-resolution (SISR), and it consists of two key parts, feature embedding net (FEN) and the image reconstruction net (IRN). FEN consists of two convolutional layers and a clique block group. The first convolutional layer tries to increase the number of channels of input, which can be added with the output of the clique block group via the skip connection. The second convlutional layer tries to change the number of channels so that they can fit the input of clique block group. The clique block group concatenates features from a sequence of clique blocks, each of which has two stages: 1) the first stage does the same things as dense block, while the second stage distills the feature further. Following the idea of resnet, a clique block contains more skip connections compared with a dense block, so the information among layers can be more easily propagated.