I am reading this Distill article Deconvolution and Checkerboard Artifacts about avoiding artifacts in images generated by neural networks.
In the section of Better Upsampling, the author compares the difference between deconvolution (i.e. transposed convolution), NN-resize then convolution, and bilinear-resize then convolution. He says:
Both deconvolution and the different resize-convolution approaches are linear operations, and can be interpreted as matrices.
Above the sentence, he shows the figure on how to interpret upsampling methods as matrices. I am confused about the figure. What is the meaning of a, b, c? How do the matrices in the bottom half correspond to the grey maps in the top half?
