PixColor: Pixel Recursive Colorization
This work addresses the challenge of automated image colorization for applications in photography and media, though it is incremental as it builds on existing neural network methods.
The authors tackled the problem of generating multiple plausible colorizations for grayscale images by using a two-stage approach with conditional PixelCNN and CNN models, resulting in more diverse and plausible outputs as validated by human raters in a Visual Turing Test.
We propose a novel approach to automatically produce multiple colorized versions of a grayscale image. Our method results from the observation that the task of automated colorization is relatively easy given a low-resolution version of the color image. We first train a conditional PixelCNN to generate a low resolution color for a given grayscale image. Then, given the generated low-resolution color image and the original grayscale image as inputs, we train a second CNN to generate a high-resolution colorization of an image. We demonstrate that our approach produces more diverse and plausible colorizations than existing methods, as judged by human raters in a "Visual Turing Test".