Extreme video compression with prediction using pre-trainded diffusion models
1–10 of 89 posts
Re: Extreme video compression with prediction using pre-trainded diffusion models
#2Can you share example videos?
Re: Extreme video compression with prediction using pre-trainded diffusion models
#3Can you share example videos?
Googling gave me the article: https://www.arxiv.org/abs/2402.08934
Which have examples in it.
Re: Extreme video compression with prediction using pre-trainded diffusion models
#4I wonder how effective a speed focused variation could be for quality among 264, 265, and AV1.
Re: Extreme video compression with prediction using pre-trainded diffusion models
#5> It can be observed that our model outperforms them at low bitrates
It can? Maybe I'm misunderstanding the graphs but it doesn't look like it to me?
Re: Extreme video compression with prediction using pre-trainded diffusion models
#6Extreme compression will be when you put in a movie and get a SORA prompt back that regenerates something close enough to the movie.
Re: Extreme video compression with prediction using pre-trainded diffusion models
#7Extreme compression will be when you put in a movie and get a SORA prompt back that regenerates something close enough to the movie.
I can imagine that in under 5 years, the movie's script plus one example still photo for each scene could do the job.
Re: Extreme video compression with prediction using pre-trainded diffusion models
#8> It can be observed that our model outperforms them at low bitrates It can? Maybe I'm misunderstanding the graphs but it doesn't look like it to me?
Graphs (especially PSNR) aren't a good way to judge video compression. It's better to just watch the video.
Many older/commercial video codecs optimized for PSNR, which results in the output being blurry and textureless because that's the best way to minimize rate for the same PSNR.
Re: Extreme video compression with prediction using pre-trainded diffusion models
#9It’s uncanny how much of the current stuff has been predicted by the sitcom -“Silicon Valley”
Re: Extreme video compression with prediction using pre-trainded diffusion models
#10Extreme compression will be when you put in a movie and get a SORA prompt back that regenerates something close enough to the movie.
I can imagine that in under 5 years, the movie's script plus one example still photo for each scene could do the job.
If we get anywhere close to that, coming up with a new economics model is going to be the prompt we'll be giving the AGI when it's ready. We'll need it.