Real-Time User-Guided Image Colorization with Learned Deep Priors

TL;DR

This paper introduces a real-time, user-guided image colorization system using deep learning that efficiently propagates sparse user hints to produce realistic colorizations, significantly improving user experience and output quality.

Contribution

The authors develop a CNN-based approach that directly maps grayscale images and sparse user hints to colorized outputs, enabling real-time interaction and incorporating learned priors from large-scale data.

Findings

System achieves real-time colorization in a single pass

Helps novice users produce realistic colorizations quickly

Incorporates user hints effectively to improve color accuracy

Abstract

We propose a deep learning approach for user-guided image colorization. The system directly maps a grayscale image, along with sparse, local user "hints" to an output colorization with a Convolutional Neural Network (CNN). Rather than using hand-defined rules, the network propagates user edits by fusing low-level cues along with high-level semantic information, learned from large-scale data. We train on a million images, with simulated user inputs. To guide the user towards efficient input selection, the system recommends likely colors based on the input image and current user inputs. The colorization is performed in a single feed-forward pass, enabling real-time use. Even with randomly simulated user inputs, we show that the proposed system helps novice users quickly create realistic colorizations, and offers large improvements in colorization quality with just a minute of use. In addition, we demonstrate that the framework can incorporate other user "hints" to the desired colorization, showing an application to color histogram transfer. Our code and models are available at https://richzhang.github.io/ideepcolor.