I’ve been re-watching star trek voyager recently, and I’ve heard when filming, they didn’t clear the wide angle of filming equipment, so it’s not as simple as just going back to the original film. With the advancement of AI, is it only a matter of time until older programs like this are released with more updated formats?
And if yes, do you think AI could also upgrade to 4K. So theoretically you could change a SD 4:3 program and make it 4k 16:9.
I’d imagine it would be easier for the early episodes of Futurama for example due to it being a cartoon and therefore less detailed.
I think you’re looking at it from the wrong direction. Instead of adding new stuff in to get the width, you could get AI to stretch the image to fit 16:9 and then redraw everything there to no longer look stretched out. Slim the people and words back down. Things like bottles on a table would be slimmed down to look like normal bottles but have the horizontal table be drawn a bit longer to fill in the space etc.
If it were done this way there would be a minimal amount of things that the AI would have to artificially create that weren’t there in the original 4:3. It would just mostly be fixing things looking wider than they should look.
Stretching while preserving proportions is still stretching. You change the spacing and relative sizing between objects.
Framing is not only about the border of the frame.
I mentioned how that would be taken care of with the bottles on tables description I made earlier. Also, the framing of shots would be changed very little.
I read the table example again and I don’t see how it describes a solution.
What about person A putting an arm over person B’s shoulder? That’d have to be a pretty long arm.
If they were close enough in a 4:3 shot to do that, the stretching would be very minimal to go 16:9. Aside from that, ai could avoid changing spaces between physically interacting people and objects.