[HN Gopher] DreamCraft3D: Hierarchical 3D Generation with Bootst...
       ___________________________________________________________________
        
       DreamCraft3D: Hierarchical 3D Generation with Bootstrapped
       Diffusion Prior
        
       Author : phil9l
       Score  : 95 points
       Date   : 2023-10-27 12:11 UTC (10 hours ago)
        
 (HTM) web link (mrtornado24.github.io)
 (TXT) w3m dump (mrtornado24.github.io)
        
       | byteknight wrote:
       | What causes all of these papers published on github without code?
        
         | echelon wrote:
         | Massive receptive AI audience.
         | 
         | The papers published on GitHub are typically presented in a
         | much more accessible and beautiful way than arXiv.
         | 
         | The downstream social traction is further signal and
         | affirmation for your results, lab, and/or company.
        
         | smusamashah wrote:
         | There is also Zero123++ which seems to be doing the same thing
         | but has code available https://github.com/SUDO-
         | AI-3D/zero123plus
         | 
         | EDIT: Just realized this one only outputs multiple images which
         | are 3D consistent, not a 3d model.
        
           | rprenger wrote:
           | I believe Zero123++ gives you the ability to generate
           | consistent images from multiple camera views, where as
           | DreamCraft3D seems to output 3D models with geometry and
           | textures if I'm understanding it right. Like I could take the
           | output of DreamCraft3D (if I had the code) and drop the
           | result into Blender for example.
        
         | T-A wrote:
         | It is not unusual for code release to follow paper release with
         | a lag of days to weeks. The top priority for a researcher is to
         | get the paper out. Code is supporting material of secondary
         | importance.
        
         | livrem wrote:
         | I was wondering why all of those papers have PDF downloads with
         | the most useless, non-descriptive, names.
         | 
         | > Paper_high_res.pdf
        
           | menacingly wrote:
           | Probably the same kind of oversight that just allowed me to
           | compile hundreds of books in a catalog each as "book.pdf"
           | 
           | It was on exactly the second download where I realized how
           | restrictive my choice of namespace was
        
           | corysama wrote:
           | The authors aren't thinking about you when they name the 87th
           | revision of their paper.pdf They just want to get some sleep.
        
         | scoopertrooper wrote:
         | The fourth line of the readme
         | 
         | > Code will come soon.
        
       | echelon wrote:
       | Unlike other areas of AI that are immediately applicable to use
       | in products (LLMs, Stable Diffusion, RVC, etc.), 3D sculpting has
       | years of further optimization before it finds its fit. These
       | sculpts are not "game ready". Their object geometry is massively
       | bloated and inefficient.
       | 
       | They're not rigged with a skeleton or morph targets. That's a
       | hard problem that some products (like rigify) can sort of solve,
       | but not for assets in this poor shape.
       | 
       | The massive VC funds being poured into this "game ready asset AI"
       | should sit on the sideline for 3-4 years and invest in a new
       | player with a fresh cap table and no baggage.
       | 
       | I'm looking to jump into this area, but the timing is off.
        
         | dleeftink wrote:
         | But isn't the point of publishing intermediate results to
         | present what is currently possibly and set the agenda for
         | future inquiries?
        
         | andybak wrote:
         | > Their object geometry is massively bloated and inefficient.
         | 
         | This came out recently which looks like a leap forward in
         | optimization: https://github.com/nv-tlabs/FlexiCubes
        
         | danielvaughn wrote:
         | I mean, alternatively, the timing is _now_. It 's a great time
         | to get a head start on it, because once it hits market-
         | readiness, there are going to be massive opportunities.
        
       | Mizza wrote:
       | This is very impressive, the best one in the space I've seen,
       | although I'd like to see some of the less cherry-picked examples.
        
         | cgijoe wrote:
         | Yup, I had the same thought. Click through the gallery to the
         | last page, and you can start to see artifacts in the examples.
         | The chicken & waffles one particularly. Although I must say, I
         | am still extremely impressed by this tech.
        
           | broast wrote:
           | Interestingly most of the artifacts, like the chicken and
           | waffles one, are on the texture and not on the mesh.
        
       | LarsDu88 wrote:
       | This is incredible.
       | 
       | All that remains is a network for rigging (and maybe retopology)
       | 
       | Indie gamedev would be revolutionized
        
         | Benjaminsen wrote:
         | Like this? https://anything.world/
        
         | kleiba wrote:
         | There would still be a long way to go, I believe. Creating a
         | consistent art style, with assets that fit into each other well
         | for a whole game world would still be very challenging, for
         | example.
        
       | dragonwriter wrote:
       | So, at the code link
       | 
       | > Code will come soon.
       | 
       | Disappointing, but also:
       | 
       | > 6 forks
       | 
       | That's... eager.
        
       | kookamamie wrote:
       | "soldier cat" - the model shows a dog.
        
         | TaylorAlexander wrote:
         | This one? That's a cat my friend.
         | https://mrtornado24.github.io/DreamCraft3D/assets_dreamcraft...
        
       | spandextwins wrote:
       | You know how many of these bullshit things we've had in the past
       | year? Lots. All of them promise something, have a long (maybe
       | even AI generated) research paper.
       | 
       | And,, most of all, NO CODE.
       | 
       | Wtf. Push your code. Or slse it doesn't exist. I have a ton of
       | these bookmarked. Still waiting for code.
       | 
       | I call bullshit.
        
       ___________________________________________________________________
       (page generated 2023-10-27 23:00 UTC)