Colorization Using Optimization

This paper is from 2004 but I’m amazed the technology hasn’t appeared in any mainstream tools yet.  The paper presents an algorithm for colorizing greyscale images with amazing detail with only a few rough sketch marks to use as a guide.

In this paper we present a simple colorization method that requires neither precise image segmentation, nor accurate region tracking. Our method is based on a simple premise: neighboring pixels in space-time that have similar intensities should have similar colors. We formalize this premise using a quadratic cost function and obtain an optimization problem that can be solved efficiently using standard techniques. In our approach an artist only needs to annotate the image with a few color scribbles, and the indicated colors are automatically propagated in both space and time to produce a fully colorized image or sequence. We demonstrate that high quality colorizations of stills and movie clips may be obtained from a relatively modest amount of user input.

At their website they show colorizing not only photos but video as well with startling accuracy.

via Colorization Using Optimization.

About the Author: Randall Hand

Randall Hand is a visualization scientist working for a federal research lab, aiding researchers to discover the insights buried within their terabyte datasets generated on some of the most powerful supercomputers in the world. He also runs VizWorld.com .

Science algorithm, color, research