Re:Deep Bilateral Learning for Real-Time Image Enhancement
by web007 on Wednesday August 02, 2017 @12:19PM
(#14911862)
They imply "human operator" level retouching, so potentially some combination of tone mapping, unsharp mask, edge enhancement, etc. as a single NN operation. It's also <30ms for 1080p on mobile, so potentially better than average speed.
[ Parent
| on HN ]
Re:Deep Bilateral Learning for Real-Time Image Enhancement
by londons_explore on Wednesday August 02, 2017 @06:26PM
(#14915247)
This is effectively "tone mapping" which is aware of context. Ie. a face and a shoe might have the exact same color, yet they can end up different colours after processing even if they appear in the same image.