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

221–230 of 243 posts

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

#221

Post by pezezin »

erhaetherth wrote: post #216
mrandish wrote: post #208

Earlier quoted context omitted.

No, I'm not concerned. When an AI is trained on a largely raw, uncurated set of low-quality data (eg most of the public internet), it's going to miss subtle distinctions some humans might prefer that it make. I'm confident that pretty quickly the majority of the general public using such AIs will begin to intuitively understand this. Just as they have developed a practical, working understanding of other complex tech…

> AI lying to deny that HP Lovecraft had a childhood pet GPT4 told me with no hesitation.

I just tested it on Copilot. It starts responding and then at some point deletes the whole text and replies with:

"Hmm… let’s try a different topic. Sorry about that. What else is on your mind?"

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

#222

Post by RVuRnvbM2e »

IanCal wrote: post #86
Aissen wrote: post #74

This is great for entertainment (and hopefully the main application), but we need clear marking of such type of videos before hallucinated details are used as "proofs" of any kind by people not knowing how this works. Software video/photography on smartphones is already using proprietary algorithms that "infer" non-existent or fake details, and this would be at an even bigger scale.

Like Ryan Gosling appearing in a building https://petapixel.com/2020/08/17/gigapixel-ai-accidentally-a...

Or white Obama https://twitter.com/Chicken3gg/status/1274314622447820801

I don't see the word "bias" appear anywhere in this work :'(

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

#223

Post by web007 »

constantcrying wrote: post #30
web007 wrote: post #23

Earlier quoted context omitted.

Why would someone ever take a 40Mbps (compressed) video and downsample it so it can be encoded at 400Kbps (compressed) but played back with nearly the same fidelity / with similar artifacts to the same process at 50x data volume? The world will never know. You're also ignoring the part where all lossy codecs throw away those same details and then fake-recreate them with enough fidelity that people are satisfied. Same…

>Why would someone ever take a 40Mbps (compressed) video and downsample it so it can be encoded at 400Kbps (compressed) but played back with nearly the same fidelity Because you can just not downscale them and compress them in the frequency domain and encode them in 200Kbps? This is pretty obvious, seriously do you not understand what JPEG does? And why it doesn't do down sampling? Do you seriously believe downscalin…

Yes, absolutely. Paychovisual encoding can only do so much within the constraints of H.264/265.

Throwing away 3/4 (half res) or 15/16 (quarter res) of the data, encoding to X bitrate and then decoding+upscaling looks far better than encoding to the same X bitrate with full resolution.

For high bitrate, native resolution will of course look better. For low bitrate, the way H.26? algorithms work end up turning high resolution into a blocky ringing mess to compensate, vs lower resolution where you can see the content, just fuzzily.

Go get Tears of Steel raw 4K video (Y4M I think it's called). Scale it down 4x and encode it with ffmpeg HEVC veryslow at CRF 30. Figure out the bitrate, then cheat - use two-pass veryslow HEVC encoding to get the best possible quality native resolution at the same bitrate as your 4x downscaled version. You're aiming for two files that are about the same size. Somehow I couldn't convince the codec to go low enough to match, so I had the low-res version about 60% of the high-res version filesize. Now go and play them both back at 4K with just whatever your native upscale is - bilinear, bicubic, maybe NVIDIA Shield with it's AI Upscaling.

Go do that, then tell me you honestly think the blocky, streaky, illegible 4K native looks better than the "soft" quarter-res version.

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

#226

Post by drra »

anigbrowl wrote: post #159
whywhywhywhy wrote: post #24

Earlier quoted context omitted.

Not if there isn't coherency between those chunks

Easily solved, just overlap by ~40 frames and fade the upscaled last frames of chunk A into the start of chunk B before processing. Editors do tricks like this all the time.

Or upscale every 4th frame for consistency. Upscaling in between frames should be much easier.

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

#227

Post by gattr »

jonplackett wrote: post #196
scns wrote: post #174

Earlier quoted context omitted.

I know two movies where the book is way better, Jurassic Park and Fight Club. I thought about putting spoilers in a comment to this one but i won't.

The lost world is also a great book. It explores a lot of interesting stuff the film completely ignores. Like that the raptors are only rampaging monsters because they had no proper upbringing having been been born in the lab with no mama or papa raptor to teach them social skills

But hey, at least we finally got the motorcycle chase (kind of) in "Jurassic World"! (It's my favourite entry in the series, BTW.)

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

#228

Post by robertlagrant »

btown wrote: post #220
robertlagrant wrote: post #200

Earlier quoted context omitted.

> there aren't any real similarities between the book and the movie; they're two separate zombie stories with the same name Funny - this is also a good description of I Am Legend.

And similarly, I, Robot, which is much more enjoyable when you realize it started as an independent murder-mystery screenplay that had Asimov’s works shoehorned in when both rights were bought in quick succession. I love both the movie and the collection of short stories, for vastly different reasons. https://www.cbr.com/i-robot-original-screenplay-isaac-asimov...

Will Smith, a strange commonality in this tiny subgenre.

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

#230

Post by jonplackett »

hobs wrote: post #217
scns wrote: post #174

Earlier quoted context omitted.

I know two movies where the book is way better, Jurassic Park and Fight Club. I thought about putting spoilers in a comment to this one but i won't.

Disagree, Jurassic Park was an amazing movie on multiple levels, the book was just differently good, and adapting it to film in the exact format would have been less interesting (though the ending was better in the book.)

I totally forgot the book ending! So much better.

I think like the motorcycle chase that they borrowed from the lost world in Jurassic world, they also have a scene with those tiny dinosaurs pecking someone to death.

Post reply on HN