[HN Gopher] WorldGrow: Generating Infinite 3D World
       ___________________________________________________________________
        
       WorldGrow: Generating Infinite 3D World
        
       Author : cdani
       Score  : 71 points
       Date   : 2025-10-27 09:31 UTC (13 hours ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | jackdoe wrote:
       | cant wait for the new diablo :)
        
         | speedgoose wrote:
         | It looks more like the Stanley parable.
        
         | pjmlp wrote:
         | With a quarter the size of the development team, 'cause
         | productivity!
        
       | embedding-shape wrote:
       | It is only a paper as of now:
       | 
       | > The code is being prepared for public release; pretrained
       | weights and full training/inference pipelines are planned.
       | 
       | Any ideas of how it would different and better compared to
       | "traditional" PCG? Seems like it'd give you more resource
       | consumption, worse results and less control, neither of which
       | seem like a benefit.
        
         | glenneroo wrote:
         | The description in the linked YouTube video for some reason has
         | more info than the github repo:
         | 
         | > We tackle the challenge of generating the infinitely
         | extendable 3D world -- large, continuous environments with
         | coherent geometry and realistic appearance. Existing methods
         | face key challenges: 2D-lifting approaches suffer from
         | geometric and appearance inconsistencies across views, 3D
         | implicit representations are hard to scale up, and current 3D
         | foundation models are mostly object-centric, limiting their
         | applicability to scene-level generation. Our key insight is
         | leveraging strong generation priors from pre-trained 3D models
         | for structured scene block generation. To this end, we propose
         | WorldGrow, a hierarchical framework for unbounded 3D scene
         | synthesis. Our method features three core components: (1) a
         | data curation pipeline that extracts high-quality scene blocks
         | for training, making the 3D structured latent representations
         | suitable for scene generation; (2) a 3D block inpainting
         | mechanism that enables context-aware scene extension; and (3) a
         | coarse-to-fine generation strategy that ensures both global
         | layout plausibility and local geometric/textural fidelity.
         | Evaluated on the large-scale 3D-FRONT dataset, WorldGrow
         | achieves SOTA performance in geometry reconstruction, while
         | uniquely supporting infinite scene generation with
         | photorealistic and structurally consistent outputs. These
         | results highlight its capability for constructing large-scale
         | virtual environments and potential for building future world
         | models.
        
           | embedding-shape wrote:
           | That seems to compare to other similar "generating infinite
           | 3D worlds" approaches, but not to traditional PCG, which
           | would give you all of that except higher quality, better
           | performance and more/better control.
        
         | tantalor wrote:
         | An _unpublished_ paper.
        
       | Garlef wrote:
       | I don't think generating virtual space is the issue.
       | 
       | It's about generating interesting virtual space!
        
         | james-bcn wrote:
         | Yep. People have been doing this kind of stuff for computer
         | games for decades. It's actually not that difficult. It's not
         | clear what novel problem is being solved here.
        
           | jsheard wrote:
           | Yeah but those traditional procgen techniques don't use AI,
           | and this one does use AI. They solved the problem of them not
           | being AI enough for the AI era. AI!
        
           | agravier wrote:
           | Do you have some particular piece of software or tech demo or
           | game in mind with interesting very large generated 3D worlds?
        
             | sirtaj wrote:
             | Valheim and No Man's Sky are ones I've played recently.
        
             | SiempreViernes wrote:
             | In Mario 64 there is a staircase you can run up forever,
             | granted it looks the same no matter how long you have Mario
             | run up the stairs, but that certainly fits "big but
             | uninteresting 3d world."
        
               | bogwog wrote:
               | > big but uninteresting 3d world.
               | 
               | I know 'interesting' is subjective, but your comment is
               | demonstrably false. Just type "mario 64 staircase" into
               | youtube, and look at the hundreds (thousands? millions?)
               | of videos and many millions of views.
        
               | f17428d27584 wrote:
               | People are interested in it as a form of trivia. It is
               | extremely uninteresting from the perspective of the
               | player and more importantly how the word was actually
               | used, which was in reference to the quality of world
               | generation.
               | 
               | Redefining "interesting" just so you can provide a
               | completely irrelevant "correction" is bad faith trolling.
        
               | bogwog wrote:
               | Not sure why you're so defensive about this. I'm not
               | trolling. Whether something is interesting or not is
               | subjective, which is my point. You might think you know
               | why that staircase is interesting to people (it's just
               | trivia), but that's just your opinion. This is a tech
               | community, so you're obviously unimpressed by the
               | technology used to make it, but most people don't care
               | about that at all.
               | 
               | There's no secret formula to culture. Some programmers
               | and AI people seem to think there is some magic AI model
               | that will be able to produce cultural hits at the click
               | of a button. If you're a boring person, you're not likely
               | to "get" why something is interesting, or why that part
               | can't just be automated away. No technology can help with
               | that.
        
             | antonvdi wrote:
             | Minecraft surely fits those criteria.
        
             | NBJack wrote:
             | Age of Empires got me into tinkering with content
             | generation. The flexible map rules were fantastic in making
             | this possible.
             | 
             | Minecraft is of course the poster child for very large
             | worlds of interest these days.
             | 
             | Dwarf Fortress crafts an entire continent complete with a
             | multi-century history, the results of which you can explore
             | freely in adventure mode.
             | 
             | Most of the recent examples of 3D worlds like the post tend
             | to do it through wave function collapse.
        
               | omnibrain wrote:
               | > Minecraft is of course the poster child for very large
               | worlds of interest these days.
               | 
               | Minecraft used to create very interesting worlds until
               | they changed the algorithm and the landscapes became
               | plain and boring. It took them about 10 year until the
               | Caves and Cliffs Update to make the world generation
               | interesting again.
        
         | jpalomaki wrote:
         | " The generated scenes are walkable and suitable for
         | navigation/planning evaluation."
         | 
         | Maybe the idea is to create environments for AI robotics traini
         | ng.
        
         | rootlocus wrote:
         | Or at least coherent.
        
         | analog8374 wrote:
         | Consider the levels generated in any roguelike.
         | 
         | Consider the patterns generated by cellular automata.
         | 
         | Both tend to stay interesting in the small scale but lose it to
         | boring chaos in the large.
         | 
         | For this reason I think the better approach is to start with a
         | simple level-scale form and then refine it into smaller parts,
         | and then to refine those parts and so on.
         | 
         | (Vs plugging away at tunnel-building like a mole)
        
           | anthk wrote:
           | Nethack/Slashem and DCSS, maybe.
           | 
           | The levels are made to fit under 80x24 terminal with maybe a
           | max of 7/8? -can't remember- rooms per level.
           | 
           | The worlds from Cataclysm DDA:Bright Nights are pretty
           | regular, and you have an overworld, labs, subways...
        
           | nonethewiser wrote:
           | >Both tend to stay interesting in the small scale but lose it
           | to boring chaos in the large.
           | 
           | I think that's a good way to put it. I started writing a
           | reply before reading your comment entirely and arrived at
           | basically the same conclusion as this but more verbosely:
           | 
           | > For this reason I think the better approach is to start
           | with a simple level-scale form and then refine it into
           | smaller parts, and then to refine those parts and so on.
           | 
           | It seems hard to get away from having some sort of
           | overarching goal, and then constantly looking back at it. At
           | progressively smaller levels. Like what is the universe of
           | the thing you are generating randomly. Is it a dungeon in a
           | roguelike? It it meant to be one of many floors? Or is it a
           | space inside a building? Is it a house? Is it an office? Is
           | the office a stand alone building or a sky scraper?
           | 
           | Perhaps a good algorithm would start big and go small.
           | - assume the universe to generate is a world             -
           | pick a location and assign stuff to generate. lets say its a
           | city                 - pick a type of city thing to generate.
           | lets say its an sky scraper                     - etc. going,
           | smaller and smaller                 - look at the city so
           | far. pick another type of city thing to generate based on
           | what has been generated so far             - look at the
           | world so far. pick another type of thing to generate
           | 
           | Or maybe instead of looking back you could pre-divide into
           | zones.
           | 
           | But then, if you want to make an entire universe (as in
           | multiple worlds), you need to just make random worlds which
           | leads to your original problem (boring chaos at large scale)
           | like this or go up another level to more intelligently
           | generate.
           | 
           | Point being, you need some sort of top down perspective on
           | it.
        
             | analog8374 wrote:
             | Here are 2 graphical examples of that strategy
             | 
             | http://fleen.org
             | 
             | https://www.flickr.com/photos/jonathanmccabe/albums/7215762
             | 2...
        
         | keyle wrote:
         | You reminded me of this
         | https://book.leveldesignbook.com/process/layout
         | 
         | And Valve I think used to have a series on level design,
         | involving from big to small and "anchor points", but I seem to
         | have misplaced the link.
        
         | otikik wrote:
         | Indeed, this has been described in the past as "The Oatmeal
         | Problem" [1]
         | 
         | [1] https://www.challies.com/articles/no-mans-sky-
         | and-10000-bowl...
        
           | zparky wrote:
           | Important to note that article was written 9 years ago and
           | NMS has received numerous content updates since. There's a
           | lot more to the game now.
        
             | nsxwolf wrote:
             | There is, but the procedural generation part is not what
             | makes it fun to me. It's what you create and how you choose
             | to "live" in the game. It really is like the real universe
             | - isotropic, the same in all directions - it only takes a
             | few hours to be overwhelmed by how pointless it all seems,
             | knowing there's an infinity of anything you discover
             | elsewhere.
             | 
             | Once you build a base or create some goal for yourself, it
             | becomes interesting.
        
           | xwiz wrote:
           | Kate Compton's GDC talk:
           | https://www.gdcvault.com/play/1024213/Practical-
           | Procedural-G...
        
       | gcr wrote:
       | This could be a great way to make backrooms horror environments!
       | 
       | I've dreamed of a NeRF-powered backrooms walking simulator for
       | quite a while now. This approach is "worse" because the mesh
       | seems explicit rather than just the world becoming what you look
       | at, but that's arguably better for real-world use cases of
       | course.
        
         | grumbelbart2 wrote:
         | > backrooms horror environments
         | 
         | True, it sounds (and looks) a lot like https://scp-
         | wiki.wikidot.com/scp-3008
        
         | endymion-light wrote:
         | i'm thinking a new version of LSD dream emulator could be
         | really interesting.
        
       | fjfaase wrote:
       | I wonder if they also have a strategy for deleting generate
       | tiles, otherwise the infinite is limited to the size of available
       | memory. I also wonder if with their method can exactly recreate
       | tiles that have been deleted. Or in other words, that they have a
       | method for generating unique seeds for all tiles. The paper does
       | not give much technical details. If the seed has a limited size
       | and there is a method for generating seeds for each 2D
       | coordinate, I wonder if it is possible to make a non-repeating
       | infinite world. I think it is not possible with a limited size
       | seed.
        
       | keyle wrote:
       | This is cool. And could be fun in games. Not sure I get the point
       | otherwise... The thought that came to mind was "Architectural
       | slop".
        
         | flohofwoe wrote:
         | Games have used procedural world generation since at least the
         | 1980s, and on 8-bit home computers. Glancing through the video
         | and webpage, the results don't look much different from what's
         | possible with traditional Wave Function Collapse tbh.
        
       | splintercell wrote:
       | Is it just me, or some of the places it generates are just not
       | realistic? Like a small area of some kind which is a dead space,
       | and there is a giant window into it.
        
         | oniony wrote:
         | Not only not realistic but also not explicit: not so much as a
         | peachy bottom in sight.
        
         | icoder wrote:
         | It's not just you. The generated stuff - in my opinion -
         | doesn't make any sense at all, with regard to structure or
         | meaning. Unless, perhaps, the aim was to generate some kind of
         | badly designed Ikea store.
        
         | hobofan wrote:
         | Yeah, I think either the method doesn't work well, or there is
         | something off with their tuning.
         | 
         | Their block-by-block generation method seems to be too local in
         | its considerations, where each 3x3 section (= the ones
         | generated based on the immediate neighbors) looks a lot more
         | coherent than the 4x4 sections and above. I think it might need
         | to be extended to be less local and might also in general need
         | to be paired with some sort of guidance systems (e.g. in the
         | office example would generate the overall floor layout).
        
       | theknarf wrote:
       | Did they reinvent "wave function collapse"
       | (https://github.com/mxgmn/WaveFunctionCollapse)?
        
         | fallat wrote:
         | No. WFC is fundamentally different from this.
        
           | ivanjermakov wrote:
           | WFC?
        
           | swiftcoder wrote:
           | Indeed, but it does serve more or less the same purpose in
           | procgen pipelines (and folks have tweaked WFC for infinite
           | worlds before[1]).
           | 
           | [1]: https://www.youtube.com/watch?v=7ffT_8wViBA
        
       | kittikitti wrote:
       | This is great and really cool! Thank you for sharing.
        
       | tantalor wrote:
       | Oh great, it's the Severance simulator.
        
       ___________________________________________________________________
       (page generated 2025-10-27 23:01 UTC)