[HN Gopher] Trellis - 3D mesh generative model
       ___________________________________________________________________
        
       Trellis - 3D mesh generative model
        
       Author : tarr11
       Score  : 119 points
       Date   : 2024-12-09 19:19 UTC (3 hours ago)
        
 (HTM) web link (trellis3d.github.io)
 (TXT) w3m dump (trellis3d.github.io)
        
       | tarr11 wrote:
       | Saw this submitted a few days ago [0], but it's a very impressive
       | demo and would like to see it get discussed here.
       | 
       | [0] https://news.ycombinator.com/item?id=42342557
        
       | vessenes wrote:
       | Um, wowowow. This is a huge leap forward in 3D Asset generation.
       | I'm downloading it right now. This feels like a combination of
       | ergonomics - pulling together multiple somewhat janky workflows -
       | better training data - and solid architecture innovation. Thanks
       | Microsoft, seriously. I'm looking forward to playing with this.
        
       | airstrike wrote:
       | Wow, these look amazing. I'm a layman, but I think this is what
       | everyone's been thinking about ever since the first NeRF demos?
       | 
       | EDIT: I went looking for those threads and found my own comment
       | wishing for this 5 years ago
       | https://news.ycombinator.com/item?id=22642628
       | 
       | The next step is to automatically add "nodes" to the 3D images
       | where the model can pivot, rotate and whatnot and then boom, you
       | have on-demand animated, interactive content.
       | 
       | Feed it some childhood photos and recreate your memories. Add an
       | audio sample from a loved one and have them speak to you. Drop
       | into VR with noise-cancelling headphones for extra immersion.
       | Coming soon! Click here to join the "Surrender Reality" waitlist
        
         | movedx wrote:
         | I'm interested to see how this affects 3D artists in game
         | development studios. Will those studios use these tools and
         | keep their artists, allowing them to push out more and more
         | content, faster, and easier, or just keep a bunch of artists
         | around, drop the other 80% of them, and use the tools to
         | _replace_ those artists?
        
           | pfisch wrote:
           | Last time I looked at these the lighting was in the textures,
           | also the meshes were asymmetrical and insane. Not usable by a
           | game dev studio.
        
             | bilbo0s wrote:
             | These models will get better. And in answer to the previous
             | question, of course they will get rid of artists. They will
             | keep just enough to do the work necessary with the help of
             | generative models, and let go of the rest.
             | 
             | The rest of the artists are not dumb, and they have a lot
             | of talent. I'm sure many of them will use the same models
             | to come up with their own games.
             | 
             | How this whole thing will play out is anyone's guess. Long
             | term, I'm hoping for new _types_ of jobs to come into
             | being. But who can say?
        
         | TacticalCoder wrote:
         | > ... and then boom, you have on-demand animated, interactive
         | content.
         | 
         | And in addition to that it's also useful for rending still
         | pictures. 2D generated images by AI so far have incorrect
         | lighting and many errors. Once it's a 3D scene rendered by
         | something like Blender (which is free), it's going to look
         | flawless: lighting is going to be correct (and configurable)
         | and all the little details that are wrong are going to be
         | easily fixed.
         | 
         | We already have insanely powerful tools and apparently from
         | here it's only going to get way more powerful real quick.
        
         | sangnoir wrote:
         | > The next step is to automatically add "nodes" to the 3D
         | images where the model can pivot, rotate and whatnot and then
         | boom, you have on-demand animated, interactive content
         | 
         | My gut says a 3D engine + this would be a superior solution to
         | the current approach of rendering rasterized video directly
         | from the latents (coincidentally, Sora got released today).
         | 
         | It may not be tractable to train a network to rig and animate
         | meshes, as well as setting up an entire scene to be a "digital
         | twin" of random videos, bit I imagine such a set up would have
         | finer-grained control over the created video while keeping
         | everything else in it the unchanged
        
       | kfarr wrote:
       | Hey this is actually really good, one of the best image to 3D
       | models I've seen so far. From an image of a bollard I was able to
       | generate a pretty good mesh. The GLB as generated was 1.2MB,
       | after compression I got it down to 35kb (!) and the fidelity is
       | good enough for most projects.
        
       | summarity wrote:
       | Pretty amazing. Scale consistency is an issue looking at the
       | scene examples, but for one-off or background assets, pretty
       | neat!
        
       | robinduckett wrote:
       | I can see the potential, but the images I give it must be very
       | far outside of its training because all it generates are weird
       | flat planes
        
         | Etherlord87 wrote:
         | Yea another miracle tool... Until you test it.
        
           | andybak wrote:
           | I've been testing it and it's the best one I've tried so far.
           | 
           | It does have failure cases but the success rate is fairly
           | high and when it works, the resulting meshes are reasonably
           | usable (maybe not to game dev production standards - but that
           | still leaves plenty of other use cases)
        
       | gsuuon wrote:
       | The ability to edit parts of the model after the fact using
       | prompts is pretty incredible
        
       | wkat4242 wrote:
       | This is great! Love it, 3D visualising can really benefit from
       | the use of Generative AI.
        
       | LarsDu88 wrote:
       | Very cool. I wonder if the fact that it featurizes 3d objects
       | using voxels can be memory intensive considering only the surface
       | voxels are actually relevant for 3d structure makin'
        
         | DaiPlusPlus wrote:
         | Octrees are memory-efficient for this kind of thing.
        
       | ThrowawayTestr wrote:
       | Think the server is overloaded, I keep getting an error
        
       | gunalx wrote:
       | Worked pretty terrible at trying to model the nix snowflake.
       | 
       | Guess its more trained on natural and biologic structures and
       | textrues, rather than more structural or symetric data.
        
       ___________________________________________________________________
       (page generated 2024-12-09 23:00 UTC)