News for hackers. Stuff that matters.

A comment on Deep Bilateral Learning for Real-Time Image Enhancement. Parent comment

Re:Deep Bilateral Learning for Real-Time Image Enhancement by londons_explore on Wednesday August 02, 2017 @06:43PM (#14915350)
I wonder how many images are required to train a network like this?

If it's in the millions, getting pre and post retouching image pairs in such a quantity is likely impractical.

[ Parent | on HN ]
Re:Deep Bilateral Learning for Real-Time Image Enhancement by vanderZwan on Thursday August 03, 2017 @03:42AM (#14917703)
Ah, right, that could also be a limitation.

Although I'm pretty sure Magnum Photos has a large quantity of images, but perhaps not all in a consistent style.

[ Parent | on HN ]