News for hackers. Stuff that matters.
Re:With Google's RAISR, images can be up to 75% smaller with... by chubs on Monday January 16, 2017 @04:42PM (#13413280)
I wonder if this could be used to upscale, say, a 1080p movie frame-by-frame to 4k? Could be fantastic if so. Imagine if it could be built into an FPGA and done in real-time by high-end TVs. Very impressive!
Re:With Google's RAISR, images can be up to 75% smaller with... by andai on Monday January 16, 2017 @05:33PM (#13413634)
The trick is that using a simple frame-by-frame approach means the details filled in only depend on the frame, not on the details which were filled in to the previous frame, so you get crazy jitter.

Deepart.io now has a video mode [0] that takes this into account.

[0] https://deepart.io/video/

Re:With Google's RAISR, images can be up to 75% smaller with... by jackvalentine on Monday January 16, 2017 @05:08PM (#13413466)
I thought that 4k devices often had the ability to do this kind of up-scaling already?
Re:With Google's RAISR, images can be up to 75% smaller with... by spyder on Tuesday January 17, 2017 @09:03AM (#13417554)
For videos it's possible to get even better results using pixel information from adjacent frames:

https://www.youtube.com/watch?v=5kaI_qr0pFA

https://people.csail.mit.edu/celiu/CVPR2011/default.html

Re:With Google's RAISR, images can be up to 75% smaller with... by Const-me on Tuesday January 17, 2017 @03:45AM (#13415960)
A friend of mine did what you want.

Contact him if you want to use the technology, dunno how much he charges for licensing.

http://www.infognition.com/VideoEnhancer/