This brings up a good point about upscaling and other enhancements done by deep learning.
These techniques are not recovering details. They're using their model to fabricate new details that looks plausible but do not necessarily match reality.
this post was submitted on 12 Mar 2023
11 points (100.0% liked)
Technology
37734 readers
515 users here now
A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.
Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.
Subcommunities on Beehaw:
This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.
founded 2 years ago
MODERATORS
It's stuff like this that makes me smirk (being a DSLR owner).
It's almost as if profit driven companies and AI/ML don't mix
Post processing wizardry should happen after the shot, as a manual action/enhancement not representational of the shot.
view more: next ›