Live data from Hacker News

AI-Powered Nvidia RTX Video HDR Transforms Standard Video into HDR Video

blogs.nvidia.com

81–90 of 119 posts

Re: AI-Powered Nvidia RTX Video HDR Transforms Standard Video into HDR Video

#81
post #16

Earlier quoted context omitted.

Not the OP, but you have to understand that 'compression of the dynamic range' is an artistic tool. Literally choosing the lighting ratio of an image is how you build out lighting for a scene. With AI overwriting these choices, you're looking at something more akin to colorization than upscaling.

I think you need to understand that it is not always a 'artistic tool' but a money or knowledge limitation.

I'm a filmmaker... I don't know a single DOP or director who wishes they could work in HD but is limited by finances or knowledge. Again, shaping light is the essence of cinematography. Modern DSLRs far surpass the dynamic range (although not the effective resolution) of 35mm film. And yet the image they produce isn't comparable. When it comes to image quality, bit depth is enormously more important than dynamic range. When it comes to creating an artistic image, dynamic range hasn't been a limit for many decades.

Re: AI-Powered Nvidia RTX Video HDR Transforms Standard Video into HDR Video

#82

That seems like a gimmick and I actually prefer SDR video that is not upscaled. There is something ugly about those AI treated videos. They look fake.

The RTX video upscaling feature works really well, there's a bug in the Firefox implementation that allows you to switch between native and upscaled side by side and the difference is striking. I don't have an HDR monitor so I can't tell you how well this new HDR feature works.

Re: AI-Powered Nvidia RTX Video HDR Transforms Standard Video into HDR Video

#84

Earlier quoted context omitted.

HDR video playback in the browser is pretty unreliable unless you're on a Mac.

In what way? I've been doing it without issue on PC longer than I've even owned a Mac.

Firefox has zero HDR support, as an example.

Re: AI-Powered Nvidia RTX Video HDR Transforms Standard Video into HDR Video

#85

A bit of a let down that the video demoing SDR->HDR conversion is itself only published in SDR. Makes as much sense as demoing a colorization tool in a grayscale video!

YouTube tends to post a downscaled SD version first, then they encode and post the higher-res versions when they get around to it. This can take days in some cases. Meanwhile the creator catches the flak...

4K processing takes just minutes, but HDR processing can take over a month to… never. There is no indication of this at all, no progress bar or eta. Just check manually every few days!

This is why everyone is giving up on HDR, it’s just too painful because the content distributors are all so bad at it, with Netflix being the sole exception.

Re: AI-Powered Nvidia RTX Video HDR Transforms Standard Video into HDR Video

#86
post #4

Earlier quoted context omitted.

Ridiculous. Like when James Cameron promoted Avatar HDR with an SDR YouTube video, while YT is perfectly capable of HDR playback.

At least as of a couple of years ago, HDR support on YouTube has been pretty bad[1]. I know they've been working to improve things since, but I kind of don't blame people for walking away from that mess. 1. https://www.youtube.com/watch?v=DwDWQyBF9II

It’s still bad. Even as a totally amateur videographer making short clips of my holidays, YouTube is not good enough.

HDR processing takes months!

The SDR down conversion is “potato quality” even to my non-expert eyes, let alone a Hollywood colourist.

Etc…

Re: AI-Powered Nvidia RTX Video HDR Transforms Standard Video into HDR Video

#87
post #27

I recently had some old super8 films shot by my parents scanned into 1080p resolution in ProresHQ. Because of the poor optics of the original camera, imperfect focus when shooting, poor lightning conditions, and general deterioration of the film stock, most of the footage won't get anywhere near what 1080p could deliver. What I'd like to try at some point is to let some AI/ML model process the frames, and instead of…

I also restored some Super 8 footage recently and had great success. The biggest win I had wasn't resolution, but slowing down the speed to be correct in DaVinci, and interpolating frames to make it 60fps using the RIFE algorithm in FlowFrames. I then used Film9 to remove shake, colour-correct, sharpen and so on.

Correcting the speed and interpolating frames added an amazing amount of detail that wasn't perceptible to me in the originals (albeit it was there).

All of this processing does remove some of the charm of the medium, so I'll be keeping the original scans in any case.

Re: AI-Powered Nvidia RTX Video HDR Transforms Standard Video into HDR Video

#88
post #44

Earlier quoted context omitted.

And what would fake detail in the real world give to you?

it doesn't have to be "fake" detail, an AI can use multiple frames to gather much more information than is available in a single frame and composite them into a much more detailed image

This makes sense, it is called super resolution, but you don't need any AI for that, but I see that AI companies are trying to hijack the term.

Re: AI-Powered Nvidia RTX Video HDR Transforms Standard Video into HDR Video

#89
post #13

I'm curious - what's the best open-source video upscaling library out there? I looked back about a year ago, and it didn't seem like there were any good open-source solutions.

It's not exactly what you're after, as it's anime specific and you need to process the video yourself (eg disassemble to frames, run the upscaler, then assemble back to a movie file), but Real-ESRGAN is very good for cleaning up old, low resolution anime: https://github.com/xinntao/Real-ESRGAN/

If you want to avoid manual processing, Anime4K runs in real time as a GLSL shader you can load into MPV (or Plex or something called IINA according to the readme) and still gives great results.

https://github.com/bloc97/Anime4K

Re: AI-Powered Nvidia RTX Video HDR Transforms Standard Video into HDR Video

#90
post #44

Earlier quoted context omitted.

And what would fake detail in the real world give to you?

I can pretty easily distinguish useful LLM output from non-useful LLM output though others on this website seem to have lots of trouble. I think I can pretty easily do the same for things in the visual field. To be honest, part of why I'm successful is that I can draw use out of imperfect tools.

Oh boy. Fake detail is well, fake. It doesn't allow you to learn anything about the world beyond self-deception. But of course, if this is what rocks your boat then be my guest.
Post reply on HN