Machine-learning photo-editor predicts what should be under your brush

Originally published at:

What is “predicts what should be under your brush” supposed to mean? I don’t see it it anywhere in the paper or the video.

I think a clear way of saying this would be “the algorithm tries to realistically modify the overall image to accommodate the user’s changes.”

That is, if the user paints black over a face’s forehead, the algorithm finds the closest real image that can match those changes, such as black hair in bangs over the forehead, and modifies the image to incorporate that hair.

I"m sure that’s cool and all if you understand those things, but here’s what I heard.

mixed with a little of this:

“a group of University of Edinburgh engineers and a private research colleague”

Wrong. They’re from Heriot-Watt University which just happens to be in Edinburgh.

All this incredible technology and they can’t produce a demo video at a sensible resolution.

This topic was automatically closed after 5 days. New replies are no longer allowed.