417
OpenAI introduces Sora, its text-to-video AI model
(www.theverge.com)
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 15 Feb 2024
417 points (95.6% liked)
Technology
59583 readers
2308 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
The compute power it would take to do that in realtime at the framerates required for VR to be comfortable for two separate perspectives would be absolutely beyond insane. But at the rate hardware improves and the breakneck speed these AI models are developing maybe it's not as far off as I think.
An Ai generated VR world would be a single map environment generated in the same way you wait at loading screens when a game starts or you move to an entirely new map.
A text to 3D game asset Ai wouldn't regenerate a new 3D world on every frame in the same way you wouldn't ask AI to draw a picture of an orange cat and then ask it to draw another picture of an orange cat shifted one pixel to the left if you wanted the cat moved a pixel. The result would be totally different picture.
I think we're talking about different kinds of implementations.
One being an ai generated 'video' that is interactive, generating new frames continuously to simulate a 3d space that you can move around in. That seems pretty hard to accomplish for the reasons you're describing. These models are not particularly stable or consistent between frames. The software does not have an understanding of the physical rules, just how a scene might look based on it's training data.
Another and probably more plausible approach is likely to come from the same frame generation technology in use today with things like DLSS and FSR. I'm imagining a sort of post-processing that can draw details on top of traditional 3d geometry. You could classically render a simple scene and allow ai to draw on top of the geometry in realtime to sort of fake higher levels of detail. This is already possible, but it seems reasonable to imagine that these tools could get more creative and turn a simple blocky undetailed 3d model into a photo-realistic object. Still insanely computationally expensive but grounding the AI with classic rendering to stabilize it's output could be really interesting.