Let there be color

Let there be color! is a project by students from Waseda University. The official title of the project is Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification. In plain english this means automatic image colorization.

The code

Here is the diagram that explains their algorithm:

/images/let-there-be-color/feature.png

The team provides the code and instructions on [this github repo][2]. If you are trying to run their code, but somehow you are stuck with some errors, send me a tweet to @migheille, and I'll try to help.

I spent some time tinkering around and coloring old historical pictures in Lebanon. A lot of the pictures are from the archive of the Library of Congress. I tried different types of images to see how good the algorithm fares and it was pretty impressive. Here are some pictures for you to look at.

Pictures of Beirut

I started with an outdoor city picture:

downtown beirut bw downtown beirut color

I moved to a picture with more greenery.

train beirut bw train beirut color

I decided to go for a more generic picture, I chose this one because I could guess some of the colors (Coca Cola logo is in red, this would be a test of the R in RGB)

coca cola sign bw coca cola sign color

I wanted to test green and blue in the same image. ( the GB of RGB)

beirut by the sea bw beirut by the sea color

Outdoor pictures

I remembered, we have cedars and old forests, so i started digging around for old "green" pictures of Lebanon. Here are some pictures of the famed cedars of Lebanon and some forests.

cedar bw Mireille Raad Blog - Image colorization

Mireille Raad Blog - Image colorization Mireille Raad Blog - Image colorization

Mireille Raad Blog - Image colorization Mireille Raad Blog - Image colorization

What is impressive about the next picture, is that the algorithm got the coloring so right for the details in the picture. (except for a small part of the water)

water and green bw water and green color

I love the shading of the soil with the different shades of brown.

Mireille Raad Blog - Image colorization Mireille Raad Blog - Image colorization

The algorithm works well on rocks, and I liked how some parts of rocks are darker.

Mireille Raad Blog - Image colorization Mireille Raad Blog - Image colorization

Mireille Raad Blog - Image colorization Mireille Raad Blog - Image colorization

Mireille Raad Blog - Image colorization Mireille Raad Blog - Image colorization

I love the detailed blue in the sky, the clouds, the shades on the trees.

Mireille Raad Blog - Image colorization Mireille Raad Blog - Image colorization

Once you start with cedar pictures, you can't stop.

Mireille Raad Blog - Image colorization Mireille Raad Blog - Image colorization

Batroun Pictures

I looked up old pictures of Batroun, I could mostly find pictures of Msailha Castle, the colored version looks surprisingly like present day.

Mireille Raad Blog - Image colorization Mireille Raad Blog - Image colorization

Mireille Raad Blog - Image colorization Mireille Raad Blog - Image colorization

Mireille Raad Blog - Image colorization Mireille Raad Blog - Image colorization

So, a big cheers to the authors of this algorithm Satoshi Iizuka, Edgar Simo-Serra and Hiroshi Ishikawa. This is truly some good science. I had a lot of fun converting /images, and I couldn't help myself get excited every time a new image got its colors back.