On: DreamFusion: Text-to-3D using 2D Diffusion

[poolio]

Co-author here - we were also surprised :) The breadth of knowledge of the visual world embedded in these 2D models and what they unlock is astounding.

[Vt71fcAqt7 → poolio]

Any word about how Nerf -> marching cubes works? I thought that was still an open problem. Is that another discovery in this research paper?

[poolio → Vt71fcAqt7]

just seems to work when the 3D model is simple and smooth

[arkis22 → poolio]

the breadth of knowledge of the visual word embedded in these lines and what they unlock is astounding

-the point