←back to thread

GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D Generation

(nirvanalan.github.io)
83 points lnyan | 2 comments | 18 Nov 24 09:46 UTC | HN request time: 0s | source
Show context
lifeplusplus ◴[18 Nov 24 12:25 UTC] No.42171767[source]▶
Potential for indie game devs
replies(1): >>42173678 #
jayd16 ◴[18 Nov 24 16:04 UTC] No.42173678[source]▶
Doubtful they'll be optimized for games. I guess if by indie you mean unoptimized then maybe...you still don't get rigs or animation.

I mean, at that point you could just make a 2d game with the input images.

replies(1): >>42173821 #
MrLeap ◴[18 Nov 24 16:15 UTC] No.42173821[source]▶
If perfect topology interferes with shipping, it's overrated.

I could think of some mechanics I could add to Tentacle Typer (my indie game) if I had 3d models of the top 2000 most used nouns. I could decimate vert soup meshes into something usable for all of them in a weekend.

Rigging would take longer. Quick and dirty pass I could do it in a month. Complex animations I wouldn't even try, but Brownian motion on some bones would breath a lot of life into things for basically no effort.

Like it or not, this kind of thing will get absorbed into some workflows eventually.

replies(1): >>42174668 #
1. jayd16 ◴[18 Nov 24 17:28 UTC] No.42174668[source]▶
The workflow is fine in theory. I just don't think the work to clean up the asset is a net gain on making it, yet.
replies(1): >>42180190 #
2. spookie ◴[19 Nov 24 04:56 UTC] No.42180190[source]▶
Same, and I say this having been making 3D reconstructions of a whole street. One should not underestimate the power of current 3D modelling tools, and modularity. The latter allows you to divide and conquer a scene by creating a set of models that can be repeated, and making different materials as needed. This is the biggest gain traditional modelling has. Not only does this make the art asset creation faster, it makes a very optimized scene.