Author Topic: ACR Super Resolution  (Read 210 times)

Jack Dahlgren

  • NG Member
  • *
  • Posts: 1324
  • You ARE NikonGear
ACR Super Resolution
« on: March 10, 2021, 19:01:01 »
Some recent news about super resolution being available in ACR
https://blog.adobe.com/en/publish/2021/03/10/from-the-acr-team-super-resolution.html

I've seen early versions of this and it is remarkably good - when you want detail.
Now to see if they come out with a Super Boke feature!


John Geerts

  • NG Supporter
  • **
  • Posts: 7253
  • Photojournalist in Tilburg, Netherlands
    • Fotoverhalen
Re: ACR Super Resolution
« Reply #1 on: March 10, 2021, 21:03:59 »
Interesting Jack. Looking forward to use it, especially on some older files.  EDIT It's now in my Adobe update.  ACR 13.2

Akira

  • Homo jezoensis
  • NG Supporter
  • **
  • Posts: 10487
  • Tokyo, Japan
Re: ACR Super Resolution
« Reply #2 on: March 10, 2021, 23:25:18 »
Thank you for the note, Jack.  Am updating my ACR.

I would be interested if the super resolution process could also reduce the moire.
"The eye is blind if the mind is absent." - Confucius

"Limitation is inspiration." - Akira

Jack Dahlgren

  • NG Member
  • *
  • Posts: 1324
  • You ARE NikonGear
Re: ACR Super Resolution
« Reply #3 on: March 11, 2021, 00:03:16 »
Thank you for the note, Jack.  Am updating my ACR.

I would be interested if the super resolution process could also reduce the moire.

I don’t know, but it is likely to be able to. Try it out!

Ann

  • NG Supporter
  • **
  • Posts: 577
  • You ARE NikonGear
    • Photographs by Ann Shelbourne
Re: ACR Super Resolution
« Reply #4 on: March 11, 2021, 00:32:09 »
The surprise to me is that one can Super Enhance JPGs and TIFFs — in addition to RAW files.


Jack Dahlgren

  • NG Member
  • *
  • Posts: 1324
  • You ARE NikonGear
Re: ACR Super Resolution
« Reply #5 on: March 11, 2021, 05:56:44 »
The surprise to me is that one can Super Enhance JPGs and TIFFs — in addition to RAW files.

I think the RAW files give it a bit more information for it to work with, but the same principle applies to whatever sort of thing you run it on,it is used to do noise removal on phone calls and video conferences.

Essentially the machine just recognizes a pattern, says “I know how that is supposed to look at higher res” then puts that new image in place. The key to being able to make this work is the large amount of images that pass through their cloud that the machine can learn from (and some powerful GPUs in the background doing math). There are doubtless elements of this which work to identify and suppress unwanted or spurious artifacts. 

I think we will see this type of computational processing find its way into cameras themselves. Maybe not for high end cameras, but if a phone cam can uprez by a factor of 4, sensors can get even smaller, or pixels can get larger and more effective in low light.