Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Hunyuan3D 2.0 – High-Resolution 3D Assets Generation

github.com

Post reply on HN
Print view View original

141–150 of 152 posts

Re: Hunyuan3D 2.0 – High-Resolution 3D Assets Generation

#141

Post by jkolio »

grumbel wrote: post #108
torginus wrote: post #91

Earlier quoted context omitted.

I think the biggest issue with stable diffusion based approaches has always been poor compositional ability (putting stuff where you want), and compounding anatomical/spatial errors that gave the images an offputting vibe. All these problems are trivially solvable (solved) using traditonal 3d meshes and techniques.

The issue with composition is only a problem when you rely on a pure text prompt, but has been solved for quite a while by ControlNets or img2img. What was lacking was the integration with existing art tools, but even that is getting solved, e.g. Krita[1] has a pretty nice AI plugin. 3D can be a useful intermediate when editing the 2D image, e.g. Krea has support for that[2]. But I don't think the rest of the traditi…

But not consistent state. The pipeline still needs to exist because most games require objects and environments to stay consistent across play sessions. That means generating from a 3D skeleton, at the very least, if not relegating genAI to production, not runtime.

Re: Hunyuan3D 2.0 – High-Resolution 3D Assets Generation

#142

Post by GistNoesis »

geuis wrote: post #35

Question related to 3D mesh models in general: has any significant work been done on models oriented towards photogrammetry? Case in point, I have a series of photos (48) that capture a small statue. The photos are high quality, the object was on a rotating platform. Lighting is consistent. The background is solid black. These normally are ideal variables for photogrammetry but none of the various common applications…

>full of holes

On the geometry side from the theoretical point of view you can repair meshes, [1], by inferring a signed or unsigned distance field from your existing mesh, then you contour this distance field.

If you like the distance field approach, there are also research work [2], to estimate neural unsigned distance fields directly, (kind of a similar way as Gaussian splats).

[1] https://github.com/nzfeng/signed-heat-3d [it works but it's research code, so buggy, not user friendly, and mostly on toy problems because complexity explode very quickly when using a grid the number of cells grows as a n^3, and then they solve a sparse linear system on top (so total complexity bounded by n^6), but tolerating approximations and writing things properly practical complexity should be on par with methods like finite element method in Computational Fluid Dynamics.

[2] https://virtualhumans.mpi-inf.mpg.de/ndf/

Re: Hunyuan3D 2.0 – High-Resolution 3D Assets Generation

#143

Post by SequoiaHope »

Mashimo wrote: post #88
SequoiaHope wrote: post #87

Earlier quoted context omitted.

Photogrammetry generally assumes a fully static scene. If there are static parts of the scene which the camera can see and also rotating parts, the algorithm may struggle to properly match features between images.

i think it's common to have dots on the rotating disk where the object is placed on.

Sure, but if the background has a lot of features it will still confuse the algorithm unless it has some special settings for ignoring the background.

Re: Hunyuan3D 2.0 – High-Resolution 3D Assets Generation

#144

Post by TeMPOraL »

ben_w wrote: post #138
TeMPOraL wrote: post #120

Earlier quoted context omitted.

Screw Metaverse. Let's make a VR holodeck. Star Trek's Holodeck is actually a good case study here (especially with the recent series, Lower Decks , going as far as making two episodes that are interactive movies on a holodeck, going quite deep into how that could work in practice both in terms of producing and experiencing them). One observation derived here is that infinite procedural content at your fingertip does…

> I'm not talking about cat pictures Caitian pictures, on the other hand… I think they were more than implying what T'Ana got up to with Shaxs.

You're right. Lower Decks was much less subtle about this than prior shows. Should've remembered since I was the one to bring it up.

Re: Hunyuan3D 2.0 – High-Resolution 3D Assets Generation

#145

Post by geuis »

andybak wrote: post #128
meindnoch wrote: post #113

Earlier quoted context omitted.

The parent explicitly asked for a mesh .

You can never be sure what someone's real intent is. They might mean "something meshlike". Personally I usually reply by asking for more info (I always have the XY Problem in my mind) but that is time consuming and some people assume you're being pendantic (I am however correct more often than not - people have posed the wrong question or haven't given critical parts of the context)

Yeah, I am explicitly asking about meshes, which is why I said that and also referenced photogrammetry. Sometimes people know what they're asking for help with.

Thanks for the links. Going to check them out this morning.

Re: Hunyuan3D 2.0 – High-Resolution 3D Assets Generation

#146

Post by geuis »

addandsubtract wrote: post #105
Mashimo wrote: post #83

Earlier quoted context omitted.

Why would that make a difference?

The OC mentioned "static lighting". If they meant static, while the platform was spinning, then the lighting would be inconsistent, because the object would change lighting with each photo. You would have to fix the lighting to the platform to spin with the object, while taking the pictures to get consistent lighting.

I think you just nailed why I have been having a hard time with my photo set. It's the lighting. Well crap, because I don't have access to the statue or studio again. Thanks for the tip.

Re: Hunyuan3D 2.0 – High-Resolution 3D Assets Generation

#147

Post by andybak »

geuis wrote: post #145
andybak wrote: post #128

Earlier quoted context omitted.

You can never be sure what someone's real intent is. They might mean "something meshlike". Personally I usually reply by asking for more info (I always have the XY Problem in my mind) but that is time consuming and some people assume you're being pendantic (I am however correct more often than not - people have posed the wrong question or haven't given critical parts of the context)

Yeah, I am explicitly asking about meshes, which is why I said that and also referenced photogrammetry. Sometimes people know what they're asking for help with. Thanks for the links. Going to check them out this morning.

Just to be clear I wasn't singling you out. I don't know anything about you.

And furthermore I also often post questions that lack sufficient context.

My point was that it's always okay to ask for clarification or to assume that there was maybe some broader contact context or to offer a suggestion that doesn't follow the most literal interpretation of the question as asked.

Re: Hunyuan3D 2.0 – High-Resolution 3D Assets Generation

#148

Post by blargey »

NBJack wrote: post #82
jsheard wrote: post #10

Earlier quoted context omitted.

I can only speak for myself, but a Metaverse consisting of infinite procedural slop sounds about as appealing as reading infinite LLM generated books, that is, not at all. "Cost to zero" implies drinking directly from the AI firehose with no human in the loop (those cost money) and entertainment produced in that manner is still dire, even in the relatively mature field of pure text generation.

It worked for Minecraft. It was rough at first, and needed plenty of tuning, but the terrain and environments it's capable of certainly have a wide audience. But as far as pure, unbridled generation goes, yeah; I'm sure there will be plenty of slop made in the coming decade.

The terrain generation is not the appeal of Minecraft, it’s the game system that lets people level that terrain into a canvas and then build their own stuff on top.

Re: Hunyuan3D 2.0 – High-Resolution 3D Assets Generation

#149

Post by nkrisc »

cma wrote: post #76
jchw wrote: post #63

Earlier quoted context omitted.

I don't know why you think that's the case regarding text models. If that was the case, there would be articles on here that are just created by only generative AI and nobody would know the difference. It's pretty obvious that's not happening yet, not the least of which because I know what kinds of slop state-of-the-art generative models still produce when you give them open-ended prompts.

Ironic how this comment exemplifies the issue - broad claims about "slop" output but no specific examples or engagement with current architectures. Real discussions here usually reference benchmarks or implementation details. (from Claude)

Excellent example. This comment contains nothing novel, substantive, or interesting.

Re: Hunyuan3D 2.0 – High-Resolution 3D Assets Generation

#150

Post by ryandamm »

geuis wrote: post #146
addandsubtract wrote: post #105

Earlier quoted context omitted.

The OC mentioned "static lighting". If they meant static, while the platform was spinning, then the lighting would be inconsistent, because the object would change lighting with each photo. You would have to fix the lighting to the platform to spin with the object, while taking the pictures to get consistent lighting.

I think you just nailed why I have been having a hard time with my photo set. It's the lighting. Well crap, because I don't have access to the statue or studio again. Thanks for the tip.

You could try generating per-view depth maps, going to a point cloud and meshing from there. (I suspect splats may reduce your accuracy as an intermediate.)

I’m not aware of a fully-baked workflow for that — though it may exist. The first step has gotten really good: the recent single-shot AI models for depth are pretty visually impressive (I don’t know about metric accuracy).

The ones I’m aware of are DUST3R and the newer MAST3R:

https://github.com/naver/dust3r https://github.com/naver/mast3r

Good luck!

Post reply on HN