> Please don't do things to make titles stand out, like using uppercase or exclamation points, or saying how great an article is. It's implicit in submitting something that you think it's important.
Sorry, I can’t seem to edit the title anymore, but I have to say it wasn’t publicized or known at the time that the CEO and kitchen were rendered virtually, including his motions etc. for the 14 second clip. I tried to fit that in the character count of the title because I didn’t think the article title was descriptive enough.
Please flag the post if it doesn’t fit the guidelines, I didn’t mean it to be clickbaity, my apologies.
It says in the YouTube video, and shows in the clips that the keynote revealed the rendering immediately as part of the show?
I didn't see the full thing, but the posture and lighting in the clips in the making-of don't look like they'd have convinced anyone? (See YouTube video avnigo links).
Is this just marketing saying water isn't wet or am I missing something?
You can spot straight away that he looks like he's in a Zoom meeting with a fake background, he has a green halo behind his hair, and after he says "Our first kitchen keynote." he moves his shoulders and you can see the background behind his shoulders move. (Edit: what the hell, the moving background is visible in the 1080p version, but not really in the 2160p one! So I guess that's YouTube's compressor's fault.)
Since they already built a very detailed model of his kitchen, it would've been more interesting if they had a multi camera setup, or even a camera that moves around, like in the BBC studio https://www.bbc.com/sport/av/olympics/58113457
And the "deepfaked" Jensen seems to me is also very easy to spot...
Or... was he in his real kitchen in 2020, and I'm just seeing things? At the start of his talk in 2021 the kitchen is very out of focus and blurred.
The kitchen in the background doesn't match the one being disassembled, you see items in a different place and far less realistic lighting in the 3D modeled one. So I think his background is real/a picture, and then they simply cut to the fake one (the version of the 2021 keynote that I see on YouTube is incredibly blurry even at the highest resolution of 1080p that I can select, so if they deepfaked the speaker, I suspect they were hiding that).
YouTube destroys video quality at 1080p especially if the original file is not "optimal". I spent a week recently testing what combinations of bit rate, resolution, and codec gets the best results at 1080p.
Short version: Upload at 4K, 2mbps x frame rate(30fps x 2mbps = 60mbps), H.265
The kitchen isn't fake and who's to say no one noticed? The article certainly doesn't say that, it says that a virtual model was made.. including of the CEO. Maybe I'm being fooled by rendering, but for more than a few minutes he stands slightly out of focus (a risk of IRL video), which doesn't seem like something you'd go to the trouble of rendering (not for a keynote where things should be perfect). Of course, now I've pointed that out maybe future fakers will consider this.
Anyway, back to the kitchen... as they said on "The Wire" follow the spatulas. On camera-left there are red, orange and pink spatulas (https://youtu.be/eAn_oiZwUXA?t=1079), they even move (https://youtu.be/eAn_oiZwUXA?t=1990).. presumably inconsistency across multiple takes and editing. Also note what's on the counter to his right. At the point they switch to the virtual kitchen (https://youtu.be/eAn_oiZwUXA?t=6470), we get the "unnecessary blurry zoom effect" (used in TV to save interpolation on eg the living room -> house -> city -> country -> planet zoom out).. now the items to his right are different (there was no American flag in that white dish just now) - there's less items, and the spatulas... well even the modellers refused to make so many, dropping the orange, red, and, pink ones from the container.
That sounds like it could be interesting. It's funny how much of our "reality" / perceived universe is simply imagined or taken for granted even without any CG involved.
Even in simple text, I can relate to you my relief at finding a news article on HN which was posted by my stealth marketing team on behalf of Nvidia today, or I can describe the tiny white kitten curled up on my chest as I type this from the couch I found on the street.
In a way, that expression will create an effect similar to the Nvidia CG project for a lot of people.
Meanwhile, I have no tiny white kitten, I'm not laying on a couch, and I don't work on a stealth marketing team. But some will go as far as visualizing what I must look like, or waxing sentimental about kittens.
Some others would even doubt the retraction of those statements, merely because of a constant inner perceptive mandate which causes them to work extra hard at never getting caught closing off possibilities.
I mean it's not as if the Turing test is immensely complicated. For VR you can just make people compare a rendering with the view of a real camera and see if people can tell the difference.
I showed Netflix's "Love Death + Robots: Ice Age"[1] to several people and no one noticed it's CGI until I pointed it out. Even then I had to point out particular details until they really believed it.
Eh? The CGI is in the freezer sure, the man and woman are 100% live action. But who didn't notice that? Or do they think a miniature civilisation actually did exist?
To me that looks exactly how they had done a lot of the freezer stuff. Sure there was some CGI in there too. But most of it looked like classical camera effects (time lapsing, special lenses, etc) rather than computer generated assets.
There’s a reason they didn’t believe you. I mean there’s obviously parts of that short that did make use of CGI but clearly it’s predominantly live action
Depending on how many shortcuts you take and how much resources you have, it could.
If it's naïevely rendered, 66 seconds times 30fps is 1800 frames, 10 minutes rendering per frame, 12 days. This scene is very simple, so I think 10 minutes is a bit much, but in any case it's not an unreasonable statement.
(The scene is so simple I feel that with PBR and some fancy postprocessing you could come very close in real time even without their RTX tech.)
I haven't seen this one and while I am sure many have missed, there's no way "nobody noticed". Of course, this is direct PR material straight from Nvidia. Such material is hard for me to read because at 50 percent is junk words and sentences
This is a bit of a weird one. Sometimes VR is super obviously rendered in a certain game engine, but sometimes, even on my now aging Vive it just looks absolutely astonishing.
I have a photogrammetry scan of some guys room as my VR home on Steam and it's genuinely eery how I have to do a double take sometimes.
CGI is much more widely used in film than I think you think it is. Half the distance/crowd shots in LotR nearly 20 years ago now were CGI, from what I remember, and e.g. the following scenes of the car sequence in Deadpool use CG humans in far more places than I’d guessed from having watched the film: https://youtu.be/C8D_o8bOeOc
The cinematics in videogames likewise can be pretty convincing, even when the gameplay itself isn’t so much.
Princess Leiah was reanimated in star wars sequels. She made it pretty deep into the uncanny valley, and died there.
No digitally rendered realistic human has ever made it through the uncanny valley. The uncanny valley is to be avoided at all costs, but many digital animators refuse to learn.
Gollum from LOTR worked well because it didn't matter that he was in the uncanny valley. He's supposed to creep you out, it suited his character.
I'd say, rendering is basically solved. The problem now is animations. Very hard to replicate all micro expressions and imperfections we have come to accept from humans. Even humans with motion capture rigs seem to be insufficient.
That said, what about the John Connor death in Terminator: Dark Fate? What's uncanny about that?
Leia and Moff Tarkin (sp?) were not convincing to me - they're incredible feats, but it just looked like a couple of video game characters stuck in the movie (I'm being a bit harsh there). One shot of Tarkin was pretty great, until he moved.
I'm not at all saying this isn't all incredible progress, but it seems like it's almost asymptotic to creating a convincing on screen effect?
Thanks all for the links and suggestions for scenes to check out.
Hmm, I would have expected that to be true in one direction from the norm but not the other - how is it that only people in the middle can't spot unnatural motion?
I'd have expected rendering and modelling to attract quite different sets of people.
Chasing photorealism in games seems misguided to me; you have to spend much more money on artists. And at the end of the day, photorealism won't make a bad game into a good game; so that money is better spent on other aspects of the game. Furthermore, if you're committed to spending that much money making a game, it will probably have a very conservative lowest-common-denominator design to recoup as much money as possible. Who will take risks and experiment when so much money is on the line? You end up with a game that is mediocre to everybody but exceptional to few. The video game equivalent of a big budget marvel movie.
Photorealism may be a worthwhile goal for VR. Even completely cartoonish games like No Man's Sky can, at times, make you forget what you are seeing is not real. This effect is only enhanced in more 'real' games (like Flight Simulator 2020, in VR).
In general though, I agree it's a waste of time. I'd much rather play Super Hot, for instance.
Although I do play Dwarf Fortress occasionally, so I might not be representative of the average demographic...
Interesting side effect: I couldn’t help but look at the people in the video and think they were CG as well. Maybe it’s watching it on the phone with less room to tell the details apart.
https://news.ycombinator.com/newsguidelines.html
Clickbait title, it was very clear it was rendered at the time and there was no attempt to hide it.