News for hackers. Stuff that matters.

A comment on Deep image prior 'learns' on just one image. Parent comment

Re:Deep image prior 'learns' on just one image by knolan on Thursday November 30, 2017 @06:50PM (#15820748)
Somewhat similar to content aware fill in Photoshop [0]. The untrained network can latch onto frequent patterns and match them to holes in the data.

Why doesn’t it paint everything white? Are these actually transparent images or are they somehow tagged?

[0]https://helpx.adobe.com/photoshop/using/content-aware-patch-...

[ Parent | on HN ]
Re:Deep image prior 'learns' on just one image by jmmcd on Thursday November 30, 2017 @07:24PM (#15820953)
Yes, for the inpainting, the parts to be painted (big white deleted areas) are supplied as masks, so it doesn't try to match them.
[ Parent | on HN ]
Re:Deep image prior 'learns' on just one image by BatFastard on Thursday November 30, 2017 @08:37PM (#15821274)
But its generating unique content in those areas...
[ Parent | on HN ]
Re:Deep image prior 'learns' on just one image by jmmcd on Friday December 01, 2017 @02:57AM (#15822595)
Yes, every "run" of the network is generating pixels in those areas, but they're not being compared against the white (deleted) pixels. On the final run of the network, they're still not being compared against anything, except by us, visually, when we look at those pixels.
[ Parent | on HN ]