Cross-Scale Internal Graph Neural Network for Image Super-Resolution (Supplementary Materials) Shangchen Zhou

In this supplementary material, we provide additional details and results to the paper. Then, we give an illustration of operation details in the GraphAgg. B presents further analysis and discussions on our proposed GraphAgg module and IGNN network. A.2 Illustration of Detailed Processes in GraphAgg To further clarify the operations in the GraphAgg, we illustrate the details as shown in Figure 1. Note that we do not consider the searching window in this discussion for simplicity.