4. Automatic colorization autoencoder
We're now going to work on another practical application of autoencoders. In this case, we're going to imagine that we have a grayscale photo and that we want to build a tool that will automatically add color to it. We would like to replicate the human abilities in identifying that the sea and sky are blue, the grass field and trees are green, while the clouds are white, and so on.
As shown in Figure 3.4.1, if we are given a grayscale photo (left) of a rice field in the foreground, a volcano in the background, and sky on the top, we're able to add the appropriate colors (right).
Figure 3.4.1: Adding color to a grayscale photo of the Mayon Volcano. A colorization network should replicate human abilities by adding color to a grayscale photo. The left photo is grayscale. The right photo is color. The original color photo can be found in this book's GitHub repository at, https://github.com/PacktPublishing...
