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

MeshAnything – Converts 3D representations into efficient 3D meshes

buaacyw.github.io

Post reply on HN
Print view View original

61–70 of 71 posts

Re: MeshAnything – Converts 3D representations into efficient 3D meshes

#61

Post by olejorgenb »

mdorazio wrote: post #40
bognition wrote: post #39

Earlier quoted context omitted.

why are polygons preferred over triangles?

It's much easier and cleaner to subdivide quads to refine shapes when modeling. For example, you can split the quads along an entire edge to get a new clean edge for manipulation (ex. to bevel it). If you try to do the same with triangles, you get a jagged mess.

This might be a naive/stupid question, but wouldn't it be relatively easy to merge triangles in the same plane into polygons automatically? (I suppose few triangles from this process would be in the same plane maybe?)

Re: MeshAnything – Converts 3D representations into efficient 3D meshes

#62

Post by johnnyanmac »

neutrinobro wrote: post #59
bognition wrote: post #39

Earlier quoted context omitted.

why are polygons preferred over triangles?

They are not. Polygons are a terrible representation since unlike triangles they do not cleanly represent a unique planar surface. With more than 3 points you will always have an ambiguity (or several) about which (numerical) plane corresponds to the actual face. For some graphics applications this may or may not matter much, but it is very important for anything using the mesh for physical computation.

Co-planar quads will always subdivide into two coplanar tris. That's the crux on why the modeling work flow works. The GPU is going to turn it into triangles anyway as long as a few fundamental rules with indices are up kept, so you're mostly getting the best of both worlds here.

Re: MeshAnything – Converts 3D representations into efficient 3D meshes

#63

Post by pennomi »

olejorgenb wrote: post #61
mdorazio wrote: post #40

Earlier quoted context omitted.

It's much easier and cleaner to subdivide quads to refine shapes when modeling. For example, you can split the quads along an entire edge to get a new clean edge for manipulation (ex. to bevel it). If you try to do the same with triangles, you get a jagged mess.

This might be a naive/stupid question, but wouldn't it be relatively easy to merge triangles in the same plane into polygons automatically? (I suppose few triangles from this process would be in the same plane maybe?)

If they’re actually in the same plane, yes. But that’s rarely the case except in hard surface modeling.

Besides, merging them unintelligently still doesn’t necessarily form clean edge loops, which are required for good model topology.

Re: MeshAnything – Converts 3D representations into efficient 3D meshes

#64

Post by xray2 »

p_l wrote: post #26
modeless wrote: post #4

Nice looking results, hopefully not too cherry-picked. Every 3D model generation paper posted on HN has people complaining that the meshes are bad, so this kind of research is welcome and necessary for generated 3D assets to be used in actual games. Weird custom non-commercial license unfortunately. Notes from the GitHub readme: > It takes about 7GB and 30s to generate a mesh on an A6000 GPU > trained on meshes with…

Honestly I like the faces limitation - use it as input for blender to further develop the model, not as final product.

I fear people who aren’t good with developing models will just use it as their base. Not bad I guess, we could use more low poly games.

Re: MeshAnything – Converts 3D representations into efficient 3D meshes

#67

Post by lmpdev »

Stevvo wrote: post #58
bhouston wrote: post #37

Definitely the best result for low polygon creation I've seen. Great job! Still triangles rather than polygons, but we are getting closer. The end goal should be: 1) Polygons, mostly 4 sided, rather than triangles. 2) Edge smoothness/creases to separate hard coders from soft corners. (Which when combined with polygons enables SubD support: https://graphics.pixar.com/opensubdiv/docs/subdivision_surfa... ) 3) UV for te…

I feel like maybe CAD would be easier? You only need represent form/edges, rather than meet all the requirements that you have for using a model for games/rendering.

Are you describing NURBs?

Re: MeshAnything – Converts 3D representations into efficient 3D meshes

#68

Post by taneq »

ramses0 wrote: post #51
alexvitkov wrote: post #33

Earlier quoted context omitted.

Real life castles were designed to withstand a siege, video game castles are designed to give off a castle vibe. Once you've achieved that you stop adding stuff, as anything beyond that just creates problems - you start killing performance, visibility starts to suffer, it's not clear what's interactive and what is decoration, gameplay starts to take a hit as the AI and player start getting stuck in the clutter, etc,…

A personal pet-peeve of mine is "movies that feature an airplane flying away and turning left off into the sunset..." ThEy NeVeR AniMaTe The FlAps!! It's like you'd have an animated motorcycle scene and they don't turn the handlebars or make the bike lean when going around a corner. Like, the graphics are _soooo_ good but then they make the danged plane turn and immersion breaks (for me).

In the same vein, any time someone plays an instrument that they don't really play, and their hands aren't moving to match the music. Or when the sound for a vehicle doesn't match the actual vehicle type - there was a CGI short film with a motorbike that was clearly a Yamaha MT-01 with its massive V-twin, and it sounded like a 600cc 4-pot rather than a tractor.

Re: MeshAnything – Converts 3D representations into efficient 3D meshes

#69

Post by spookie »

Joel_Mckay wrote: post #21
spookie wrote: post #15

Earlier quoted context omitted.

That's fair, as someone pretty proficient in 3D modelling I understand your point. However, it also boils down to the scale of the project. Imagine recreating part of real life city, creating a digital twin, for scientific purposes (testing human behaviour in fire hazards, or simply iterating on better park planning and road design for greater perceived safety). There's a lot to be done, and it's difficult to use pro…

Procedural emission of textures, biomes and cities is not ML/AI generated... Also physics simulation of erosion for landscapes may look natural to most people. The problem is when groups start gleaning styles and artwork from 3rd parties to make something in the same style... they cross an ethical line, and a legal one in some situations (even if the original work is completely isolated from the output.) Thus, while…

Oh, for sure. Wholeheartedly agree. We are little by little eroding the foundations of an economic system which allows individuals to get recognized and rewarded for their hard work.

I may have not worded things well, I was trying to speak of modern 3D reconstruction methods, such as NeRF or Neuralangelo. I can see good uses for them, as I need to fool the senses reliably (participants will be taken to a VR world... mimicking a real place). But as many things in this field, the reality is that these methods aren't up to snuff. Still, it would be nice to be able to capture reality for non commercial purposes.

As for Polyhaven, haven't donated yet... but I hope to do so soon :)

Re: MeshAnything – Converts 3D representations into efficient 3D meshes

#70

Post by spookie »

jgord wrote: post #17
spookie wrote: post #12

Earlier quoted context omitted.

Could you go more in depth with your approach? Sounds really usefull for man made structures!

ahh.. looking for investment, so reticent to talk about the internals. Basically does a lot of matmulls and sampling to find good good planar fits... Most of these sample datasets took an hour to compute, using 12 threads on a midrange CPU... should be doable in seconds if ported to a highend GPU.

Understandable! Thanks for what you've shared. I'm doing academic work on something that could leverage a digital twin, hence my interest.

There are many uses for this tech, particularly in less techy crowds that still make significant use of traditional photogrammetry.

Your solution, if local, could give a significant advantage over other products such as Polycam. Again, if local, you could allow for much bigger scans (wink for those doing architecture, particularly those in the restoration field). Anyhow, hope you get that funding!

Post reply on HN