Image Colorization Using a Deep Convolutional Neural Network
This addresses the challenge of automated image colorization, particularly for computer-assisted art applications, but appears incremental as it adapts existing neural network techniques.
The paper tackles the problem of colorizing grayscale images by using a deep convolutional neural network to combine content from a grayscale image with style from a semantically similar color image, resulting in interesting colorization of ukiyo-e paintings.
In this paper, we present a novel approach that uses deep learning techniques for colorizing grayscale images. By utilizing a pre-trained convolutional neural network, which is originally designed for image classification, we are able to separate content and style of different images and recombine them into a single image. We then propose a method that can add colors to a grayscale image by combining its content with style of a color image having semantic similarity with the grayscale one. As an application, to our knowledge the first of its kind, we use the proposed method to colorize images of ukiyo-e a genre of Japanese painting?and obtain interesting results, showing the potential of this method in the growing field of computer assisted art.