[HN Gopher] Infinigen: Infinite Photorealistic Worlds Using Proc...
___________________________________________________________________
Infinigen: Infinite Photorealistic Worlds Using Procedural
Generation
Author : KolmogorovComp
Score : 267 points
Date : 2024-12-22 09:59 UTC (1 days ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| guld wrote:
| Really cool project.
|
| Some questions to ML/AI researchers here on HN:
|
| - Are there any ML/AI papers out there that trained on this? E.g.
| training robots in virtual environments?
|
| - What data sets are used today in the ML/AI space to train
| robots?
| nobrains wrote:
| From the video: "Infinigen is 100% procedural. Math rules only.
| Zero AI. Just graphics."
|
| .
|
| Timestamp: https://youtu.be/6tgspeI-GHY?t=107
| oneeyedpigeon wrote:
| "Zero AI" - nice to end the year with something so
| refreshing!
| cantpostcanceld wrote:
| The question wasn't "does this use AI". It was, "does any AI
| use this".
| guld wrote:
| Exactly, thanks.
|
| Did some light digging and found some related papers:
|
| - https://robogen-ai.github.io/
|
| - https://genesis-embodied-ai.github.io/, related HN
| thread: https://news.ycombinator.com/item?id=42457213
|
| - https://paperswithcode.com/datasets?q=robot&v=th&o=match
|
| These use other data sets, however.
| thrwthsnw wrote:
| He's asking if anyone is training using data created from a
| system like this, not if this uses AI.
| Flenkno wrote:
| I'm pretty sure i saw a video from Nvidia research using
| generated environments for training robots etc.
|
| Can't find it quickly though.
|
| Nvidias Omniverse is one of the core things though
| schaefer wrote:
| If you look up the nvidia keynote from 2024, omniverse,
| robotics, and digital twins are discussed at length [1]. The
| relevant parts are near timestamp: 1 hour 34 minutes
|
| [1]: https://www.youtube.com/live/Y2F8yisiS6E
| fix-your-meta wrote:
| your meta tag descriptions need to be updated and are showing
| placeholder content when shared
| NBJack wrote:
| Hasn't this been posted before? It's cool, I agree, but it's been
| around for a few years. Has there been an update?
| HelloUsername wrote:
| Correct. 18-Jun-2023. 76 comments.
| https://news.ycombinator.com/item?id=36376071
| tanepiper wrote:
| Not even subtle with that Matrix-like intro
| taneq wrote:
| That is what they were going for, yes.
| Stevvo wrote:
| The indoor scenes look completely plausible, but the outdoor
| leaves a lot to be desired. Very much behind the state of the
| art.
| pjc50 wrote:
| Behind several versions of No Man's Sky, let alone whatever
| madness the LLM people have been cooking.
| ramon156 wrote:
| NMS isn't open source nor for the same purpose
| sirobg wrote:
| What's the state of the art?
| dualogy wrote:
| So what IS the state of the art that's also FOSS, perhaps even
| as-a-library, and non-gen-AI (I'm thinking interactive/game-
| dev/realtime use-cases)?
| Stevvo wrote:
| Not open source, but Gaia is widely used in games and movies.
| Can do some cool things like simulated vegetation
| growth/distribution.
| supermatt wrote:
| You are probably thinking of gaea - not gaia. Gaia is also
| a world generator but not as widely recognised as gaea (and
| gaia is only implemented as a unity plugin IIRC).
| guerrilla wrote:
| You have to admit the sea water was way better than any video
| game today. The rest though, yeah.
| anentropic wrote:
| it's unclear from the readme - is this infinite as in can
| generate infinite variations on a scene, or infinite as in
| generates an infinite world?
| BaudouinVH wrote:
| Previously : https://news.ycombinator.com/item?id=36373494
| api wrote:
| The fact that this is possible feels like it says something about
| the universe-- that there is not as much information in our
| environment as we think there is.
|
| This in turn could explain the unreasonable effectiveness of
| brains -- especially small ones like animal brains -- at modeling
| and operating in the world.
| imiric wrote:
| That's a very superficial way of looking at the universe.
|
| Existence is not limited to whether or not it's observed.
| Brains have evolved to only gather the minimum amount of
| information required to keep the organism alive in its
| particular environment. But there is an unfathomable amount of
| complexity in the universe, even in the things we _can_
| perceive.
|
| For 3D modeling specifically these details don't matter, which
| is why we're able to approach photorealism. The renders look
| good enough to fool our brains into thinking that we're looking
| at the object as it would appear in the real world. They're a
| good approximation of visual aspects, but they're far from a
| good representation of real world objects. We don't have nearly
| enough compute for that. We've only recently gained the ability
| to model how light behaves in the real world in real-time, and
| even that is an approximation.
|
| Anyway, Infinigen looks like a cool product. It's great to see
| classical simulations instead of AI for a change.
| jrflowers wrote:
| >The fact that this is possible feels like it says something
| about the universe
|
| Similarly, the character models in Final Fantasy 7 say
| something about the human endocrine system. Aeris clearly reads
| as human despite you not being able to see her adrenal glands
| so maybe they don't exist in real life
| mensetmanusman wrote:
| The information density is large, our perception (i.e. the
| universe perceiving itself) filters for our particular length
| and time scale.
| luskira wrote:
| > "The fact that this is possible feels like it says something
| about the universe"
|
| the map is not the territory
| phyalow wrote:
| I noticed several prominent Chinese universities in the authors
| list. Doesnt this prima facie imply a breach of the chip
| sanctions/export rules?
| nxobject wrote:
| The papers mention that the co-authors did research while
| affiliated with Princeton.
___________________________________________________________________
(page generated 2024-12-23 23:01 UTC)