Automatic Colorization of Grayscale Images

Colorization of grayscale images is a simple task for the human imagination.

Researchers from the Toyota Technological Institute at Chicago and University of Chicago developed a fully automatic image colorization system using deep learning and GPUs. Their paper mentions previous approaches required some level of user input.

Using a TITAN X GPU, they trained their deep neural network to predict hue and chroma distributions for each pixel given its hypercolumn descriptor. The predicted distributions then determine color assignment at test time.

Automatic Colorization examples 1
Fully automatic colorization results – left is the input, middle is the result using the researcher’s method and right is the ground-truth.

With multiple applications that can benefit from automatic colorization (such as historical photographs and videos, artist assistance), the research strives to make colorization cost-effective and less-time consuming.

Automatic Colorization examples 2
Historical black and white images that are hard to differentiate from real color images.

Read the entire paper >>

6 thoughts on “Automatic Colorization of Grayscale Images

  1. Nicholas Perry on April 21, 2016 at 2:23 pm said:

    That’s amazing.

  2. Austin Daniel on April 22, 2016 at 6:25 am said:

    Pretty sure this implementation could be done with lower end cards. The image resolution would be limited due to a lower amount of VRAM but the only other real difference between the Titan X and even the 950 is performance. All the same technologies are present.

  3. William Gacquer on April 22, 2016 at 7:04 am said:

    Excellent!

  4. Curtis Ling on April 24, 2016 at 10:34 pm said:

    a 980ti would be able to do it…

  5. Craig Cherry on April 25, 2016 at 9:37 am said:

    Impressive result, but colorizing historical photos is a horrible application of it. Personally, I’d rather see the real thing (limited as it may have been by the technology of the day) instead of a plausible fake.

  6. XenoMuta on January 1, 2017 at 8:51 am said:

    Can’t wait to see NASA “moon mission” and “mars” photos in their real color.