First let me make the short tangent about what I want to talk about:
Upscaling of images refers to computer programs that increase the image quality of photos. They generally come in roughly 3 flavors:
  • Resolution increases: Just cutting all pixels in 4. A worthless technology from 20 years ago
  • Vector based upscaling: besides increasing the resolution these upscaling methods detected vectors of hard lines/edges or color transitions which sometimes even deals with some smaller artifacts
  • AI based upscaling which invents additional detail out of thin air into images
I have been interested in the later since roughly 2016. We digitized old family photos made on film which look wonderful. But unfortunately in the early 2000s we switched to early digital cameras that look like potatoe. But I'm also interested in making my current iPhone photos even better. I'm sure, you can think of a reason why you'd be interested in this technology as well.

The current situation

One of the great technologies in this field are DLSS by Nvidia and FSR by AMD. They're more targeted towards live footage of gaming instead of single images.
There are consumer products like waifu2x or upscayle.
Then there are tools like real_esrgan or python ISR.
All of them have in common that they do blow up the file size tremendously, do increase the quality a bit but don't really invent much detail and do give everything the cartoonish AI look.

What now?

Sure, maybe it was too much to ask for to turn my 4mb iPhone photos into 30mb full frame professional camera photo. But a 150mb waifu cartoon image seems weak
Am I the only one frustrated by this? While generative AI for text or brand new art makes leaps the upscaling lacks behind. If there is no demand in the world for this, it will never improve.
Why would I want to add false information to my photos? I also have photos taken with early digital cameras. I just cherish them as they serve me to remember how much the technology has improved.
reply
I understand that. Different tastes, I guess.
You probably don't want to hear that but every camera already does have false information in it that wasn't there in reality. Every smartphone does, dedicated cameras are more subtle but don't invent nothing either.
reply
I don't mind hearing it. In fact, in addition to the noise from the camera and the HDR algorithms and so on, I do sometimes lightly edit my own photos (correcting color/contrast/brightness and/or cropping).
Recently there was an article about the boundaries of ethical photo editing regarding the NYT photos of the Riot mining farm in Texas, but I cannot find the link.
Falseness and manipulation bother me quite a lot. I can see someone wanting to use AI to manipulate others, but to manipulate their own photo library? My photos are my diary, and I don't want it to look wonderful above all, I want it to be truthful first.
As you said, different tastes.
reply
My photos are my diary, and I don't want it to look wonderful above all
I do that as well
I want it to be truthful first.
I don't think a tree in the background going from green blop to individual leaves or a pullover getting the jersy-knit that it also had in reality is untruthful. It's a better experience for me when looking at old photos and remembering the past, it's more immersive for me
reply