Attempts colourizing NASA Apollo B/W photos with AI

Greetings,

 

 

I have been thinking about setting up a machine-learning system that has been trained with colour Apollo photos. Once a data model has been generated I will try and have it colourize the black and white Apollo photos.

 

Last week I finished building a new monster computer with an RTX 2080 Super.

The RTX lineup contains special Tensor cores which accelerate deep-learning.

 

Deep-learning/machine-learning/convoluted neural networks have been used to automatically colourize B/W photos by using hundreds of thousands of colour photos as a reference. Its even possible to colourize B/W video this way.

 

 

One such program is DeOldify: jantic/DeOldify

And this website: ColouriseSG

 

I don't know if it will work with the amount of colour photos avaible, but I will be giving it a shot. Generating a dataset from the colour photos may take several days. DeOldify advices the even higher end RTX 2080 Ti with 11 gigabytes of video memory, I got the model just below it with 'just' 8 gigabytes.

 

I think DeOldify is by far the best documented and wildy used image-learning program. So this is the one I will be using.

 

To get an idea of what deep-learning can achieve, here is a model trained on 1.3 million photos:

ColouriseSG

 

Hopefully we'll be able to get some interesting results.

 

More later.

I understand, colorizing black and white carries a commercial value. It can be an interesting test case for improving machine learning models, or could be a fun project at home. I however don’t care much for viewing old black and white masterpieces in color. I cannot imagine watching Psycho or Metropolis in color. Those movies were envisioned with black and white in mind. Their blending of forms, textures, lighting, most importantly their character and mood completely integrate with black and white, in my opinion.