Cool new style-transfer tech from Adobe; Making apples into oranges

Photographic style transfer & Adobe go way back. In 2003 we shipped Match Color, and in 2006 researcher Sylvain Paris was posting results that we sneak-peeked in 2010 and again later as the tech evolved. Now the company is working with Cornell on a deep-learning-based approach.


PetaPixel provides fun examples & details:

[W]hen you put in two photographs, the neural network-powered program analyzes the color and quality of light in the reference photo, and pastes that photo’s characteristics onto the second. This includes things like weather, season, and time of day—theoretically, a winter’s day can be turned into summer, or a cloudy day into a glorious sunrise. […]

It’s important to note that the software does not alter the structure of the photo in any way, so there’s no risk of distorting the lines, edges or perspective. The entire focus is on mimicking the color and light in order to copy the “look” or “style” of a reference photograph onto a new shot.

It’ll be fun to take this next generation for a spin (hopefully soon!).

On a related (?) note, I enjoyed this tweet: “This is the first thing i’ve seen an AI do that has truly terrified me: [see below]” 


One thought on “Cool new style-transfer tech from Adobe; Making apples into oranges

Leave a Reply

Your email address will not be published. Required fields are marked *