Automatic Controllable Colorization via Imagination

TL;DR

This paper introduces an automatic colorization framework with an imagination module that generates multiple reference images for coloring, enabling iterative editing and improved flexibility over previous methods.

Contribution

It presents a novel framework that uses a pre-trained image generation model and a reference refinement module for controllable, iterative colorization.

Findings

Outperforms existing algorithms in editability and flexibility

Enables localized and iterative modifications of colorization results

Demonstrates superior results through extensive experiments

Abstract

We propose a framework for automatic colorization that allows for iterative editing and modifications. The core of our framework lies in an imagination module: by understanding the content within a grayscale image, we utilize a pre-trained image generation model to generate multiple images that contain the same content. These images serve as references for coloring, mimicking the process of human experts. As the synthesized images can be imperfect or different from the original grayscale image, we propose a Reference Refinement Module to select the optimal reference composition. Unlike most previous end-to-end automatic colorization algorithms, our framework allows for iterative and localized modifications of the colorization results because we explicitly model the coloring samples. Extensive experiments demonstrate the superiority of our framework over existing automatic colorization algorithms in editability and flexibility. Project page: https://xy-cong.github.io/imagine-colorization.