Viewing profile — bmpoole

should work, and there are tons of new differentiable mesh and volumetric representations to try!

Aha thank you, this is helpful. Agreed there is much research needed to get this working but hopefully not too far off: https://twitter.com/kkpatain/status/1575758085821706240

Great question! Our team has been working on text-to-3d for ~1.5 years starting with https://ajayj.com/dreamfields . We had hoped that we could swap the contrastive CLIP model in D…

it's a good idea :)

With smooth enough geometry converting NeRFs to meshes with marching cubes works pretty well. Would you say the topology of meshes on our website are still too incoherent for riggi…

not yet, but see the appendix of the paper for pseudocode. the core update step from the diffusion model that powers dreamfusion is surprisingly simple and easy to implement.

hi folks, ben p from the dreamfusion paper here. happy to answer qs for the next ~hour!

I think you're both right! It is incredible that the 2D model knows enough about the visual world to produce many objects from all angles, but the 3D model is essential for gluing …

directly training a NeRF on a single image is a terribly unconstrained problem that would lead to a volume that looks bad when the viewpoint changes. the gist of render + use diffu…

yep our fixed strategy for view-dependent prompting is silly and there is tons of room for improvement!

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

Yes, this is often a problem. We use view-dependent prompts (e.g. "cat wearing sunglasses, back view") but the pretrained 2D model often does not do a good job of interpreting non-…

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.