Wednesday, November 7, 2007

Colorization Using Optimization

A couple of months ago I have mentioned a new revolutionary method to resizing images (Siggraph) from Dr Ariel Shamir and Shai Avidan of the Efi Arazi School of Computer Science that Adobe is now trying to integrate in their products.

Now applying the same techniques Anat Levin, Dani Lischinski and Yair Weiss had done it again but this time with a process to better colorize your images and videos.

What do you mean by this and in what aspect this could change our way of tint our images and videos?

Here is a quote from their web page mentioning what this project is all about.


Colorization is a computer-assisted process of adding color to a monochrome image or movie. The process typically involves segmenting images into regions and tracking these regions across image sequences. Neither of these tasks can be performed reliably in practice; consequently, colorization requires considerable user intervention and remains a tedious, time-consuming, and expensive task.

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.

--- END OF QUOTE ---

A detail documentation can be found here.
And if you want to dig more on this the Matlab code of the algorithm can be downloaded here.

Again, one of these days this would be implemented, for sure, on Photoshop or similar programs.

Post a Comment