We evaluate our algorithm using a "colorization Turing test," asking human participants to choose between a generated and ground truth color image. The system is implemented as a feed-forward pass in a CNN at test time and is trained on over a million color images. We embrace the underlying uncertainty of the problem by posing it as a classification task and use class-rebalancing at training time to increase the diversity of colors in the result. We propose a fully automatic approach that produces vibrant and realistic colorizations. This problem is clearly underconstrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorizations. Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. ![]() Please enjoy our results, and if you're so inclined, try the model yourself! There has been some concurrent work on this subject as well. We include colorizations of black and white photos of renowned photographers as an interesting "out-of-dataset" experiment and make no claims as to artistic improvements, although we do enjoy many of the results! This is partly because our algorithm is trained on one million images from the Imagenet dataset, and will thus work well for these types of images, but not necessarily for others. Some failure cases can be seen below and the figure here. ![]() However, there are still many hard cases, and this is by no means a solved problem. We believe our work is a significant step forward in solving the colorization problem. Welcome! Computer vision algorithms often work well on some images, but fail on others.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |