Colorful Image Colorization
Richard Zhang, Phillip Isola, Alexei A. Efros

TL;DR
This paper presents a fully automatic, CNN-based method for vibrant image colorization that produces realistic results and enhances self-supervised feature learning, outperforming previous approaches in human perception tests.
Contribution
It introduces a classification-based approach with class rebalancing for diverse, realistic colorization and demonstrates its effectiveness as a pretext task for feature learning.
Findings
Successfully fools humans in 32% of colorization Turing tests
Achieves state-of-the-art results in self-supervised feature learning benchmarks
Produces vibrant, realistic colorizations without user interaction
Abstract
Given a grayscale photograph as input, this paper attacks the problem of hallucinating a plausible color version of the photograph. This problem is clearly underconstrained, so previous approaches have either relied on significant user interaction or resulted in desaturated colorizations. We propose a fully automatic approach that produces vibrant and realistic colorizations. 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. 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 evaluate our algorithm using a "colorization Turing test," asking human participants to choose between a generated and ground truth color image. Our method successfully fools humans on 32% of the trials,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Advanced Image and Video Retrieval Techniques · Image Enhancement Techniques
MethodsColorization
