bmpoole

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!

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 diffusion model to refine is a great idea though and core to our method! the details of how to use the diffusion model for this refinement was the challenge, but once we figured that out it... just worked :)

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

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.