Live data from Hacker News

Trellis – 3D mesh generative model

trellis3d.github.io

51–60 of 84 posts

Re: Trellis – 3D mesh generative model

#52
post #22

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,…

>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. The next step is to generate models with higher quality mesh topology that allows animation and editing without breaking the mesh. I've done a lot of retopologizing and if I (or AI) were to rig these models as-is there would be all kinds of shad…

At this point maybe meshes are not the best representation for animation and editing. We can just use latents of neural networks

Re: Trellis – 3D mesh generative model

#54
post #28
post #22

Earlier quoted context omitted.

>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. The next step is to generate models with higher quality mesh topology that allows animation and editing without breaking the mesh. I've done a lot of retopologizing and if I (or AI) were to rig these models as-is there would be all kinds of shad…

Anywhere you'd recommend a hobbyist can learn more about remeshing or feature detection?

https://blog.yarsalabs.com/blender-topology-guide/

https://cgcookie.com/posts/guide-to-clean-topology

Re: Trellis – 3D mesh generative model

#55
post #3

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.

It's a game changer

Re: Trellis – 3D mesh generative model

#56
post #42

Wow, that's amazing.. I think this is the first time I've felt sick to my stomach watching AI generated content.. A sadness rush over me. Because these look so good, like every soul-less super-high quality shovel-ware asset ever made. I'm not putting it down, it truly is an amazing achievement, and it feels like it marks the end of hand-made assets. I don't even feel bad for the artists, I just feel bad for myself, b…

> I want to walk worlds that arose in the minds of others, not just worlds

A significant portion of game developers hate level design and the only reason they don't do procedural is because it's hard, so they are forced to build hand-crafted worlds. I'm one of those and I would find it pretty hilarious if anyone played my game thinking the levels "arose" in my mind, like I'm some kind of profound artist. I take great pride in other aspects of game development, but my level design is not one of those.

Re: Trellis – 3D mesh generative model

#59
post #41

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,…

As a newly minted 3d printer owner next step is accurate dimensions, material and nozzle diameter awareness ;) then some CAD-like support where you can specify constraints on… things?

This isn't anything parametric but I 3d printed a model from Trellis https://news.ycombinator.com/item?id=42375951

Re: Trellis – 3D mesh generative model

#60
post #15

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,…

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?

Studios don't have that many artists already - most of the "heavy lifting" is outsourced to asset production companies in China. I can see a future where these are replaced by AI and the main job of the in-house artists is to fix problems with the generated output.
Post reply on HN