Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

VideoGigaGAN: Towards detail-rich video super-resolution

videogigagan.github.io

Post reply on HN
Print view View original

1–10 of 243 posts

Re: VideoGigaGAN: Towards detail-rich video super-resolution

#3

Post by philipov »

constantcrying wrote: post #2

The first demo on the page alone shows that it is a huge failure. It clearly changes the expression of the person. Yes, it is impressive, but it's not what you want to actually "enhance" a movie.

It doesn't change the expression - the animated gifs are merely out of sync.

This appears to happen because they begin animating as soon as they finish loading, which happens at different times for each side of the image.

Re: VideoGigaGAN: Towards detail-rich video super-resolution

#4

Post by turnsout »

constantcrying wrote: post #2

The first demo on the page alone shows that it is a huge failure. It clearly changes the expression of the person. Yes, it is impressive, but it's not what you want to actually "enhance" a movie.

I agree that it's not perfect, though it does appear to be SoTA. Eventually something like this will just be part of every video codec. You stream a 480p version and let the TV create the 4K detail.

Re: VideoGigaGAN: Towards detail-rich video super-resolution

#5

Post by ethbr1 »

turnsout wrote: post #4
constantcrying wrote: post #2

The first demo on the page alone shows that it is a huge failure. It clearly changes the expression of the person. Yes, it is impressive, but it's not what you want to actually "enhance" a movie.

I agree that it's not perfect, though it does appear to be SoTA. Eventually something like this will just be part of every video codec. You stream a 480p version and let the TV create the 4K detail.

So, DLAA for video instead of games?

https://en.m.wikipedia.org/wiki/Deep_learning_anti-aliasing

Re: VideoGigaGAN: Towards detail-rich video super-resolution

#6

Post by constantcrying »

turnsout wrote: post #4
constantcrying wrote: post #2

The first demo on the page alone shows that it is a huge failure. It clearly changes the expression of the person. Yes, it is impressive, but it's not what you want to actually "enhance" a movie.

I agree that it's not perfect, though it does appear to be SoTA. Eventually something like this will just be part of every video codec. You stream a 480p version and let the TV create the 4K detail.

Why would you ever do that?

If you have the high res data you can actually compress the details which are there and then recreate them. No need to have those be recreated, when you actually have them.

Downscaling the images and then upscaling them is pure insanity when the high res images are available.

Re: VideoGigaGAN: Towards detail-rich video super-resolution

#7

Post by metalrain »

Video quality seems really good, but limitations are quite restrictive "Our model encounters challenges when processing extremely long videos (e.g. 200 frames or more)".

I'd say most videos in practice are longer than 200 frames, so lot more research is still needed.

Re: VideoGigaGAN: Towards detail-rich video super-resolution

#8

Post by chompychop »

metalrain wrote: post #7

Video quality seems really good, but limitations are quite restrictive "Our model encounters challenges when processing extremely long videos (e.g. 200 frames or more)". I'd say most videos in practice are longer than 200 frames, so lot more research is still needed.

I guess one can break videos into 200-frame chunks and process them independent of each other.

Re: VideoGigaGAN: Towards detail-rich video super-resolution

#9

Post by turnsout »

constantcrying wrote: post #6
turnsout wrote: post #4

Earlier quoted context omitted.

I agree that it's not perfect, though it does appear to be SoTA. Eventually something like this will just be part of every video codec. You stream a 480p version and let the TV create the 4K detail.

Why would you ever do that? If you have the high res data you can actually compress the details which are there and then recreate them. No need to have those be recreated, when you actually have them. Downscaling the images and then upscaling them is pure insanity when the high res images are available.

So streaming services can save money on bandwidth
Post reply on HN