Using deep learning to create professional-level photographs


#1

Google shows us how they’ve used AI to create good photographs. They wanted to see how machines can be taught subjective concepts, so they created “an experimental deep-learning system for artistic content creation.”

The artificial intelligence Google built aims to mimic the workflow of a real professional photographer. It roams landscape panoramas found in Google Street View and hunts for the best compositions. Once it finds a nice-looking photo, it uses post-processing techniques to improve the look of the shot like photographers do in Photoshop or Lightroom.

Example:

Read more:


#2

I thought that this was incredible, shows how fast and far deep learning has gotten


#3

One day (soon I think) cameras will offer this as part of their automation modes


#4

What if they could tell you that the subject you’re photographing has been done already too many times haha? Like if you try to shoot someone holding a smokebomb in the forest the camera just freeze :joy:


#5

:smiley:

“Error 404”

It appears that you’re blatantly plagiarising HCB. Please reinsert subject and try again


#6

I picture it like Marvin the paranoid android from the Hitchiker’s guide to the galaxy. A very depressed and monotone voice saying “Oh, another picture of your hand holding a leaf in front of the camera in a forest… just wonderful… not”