🚀Create complex, modular 3D assets and scenes.🚀 Introducing #MoCA (Mixture-of-Components Attention), a new sparse attention method for compositional 3D generation. It scales to *many * components. paper: code:

Great visuals, but impossible to validate scientifically. This is the ~10th paper from this team on the same closed-source dataset. Without public splits, we can't even confirm the eval data isn't in training. The real 'novelty' here seems to be the private dataset, not the model

There are already several tools out there for generating meshes from 3D parts and they all produce similar results. What's needed isn't another approach to part generation, but an improvement in the fidelity and accuracy of the parts generated.

This rocks :O thanks so much for sharing!

Oh wow, that's some serious stuff, Tengfei! This MoCA sounds quite promising, no?

😱

Nice

that is cool !!

love this!

🔥