A working implementation of text-to-3D DreamFusion, powered by Stable Diffusion

Re:A working implementation of text-to-3D DreamFusion, power... by shadowgovt on Thursday October 06, 2022 @01:24PM (#33111173)

Thank you for the clarification; I hadn't grokked the algorithm yet.

That's interesting for a couple of reasons. I can see why that works. It also implies that for closed objects, the voxel data on the interior (where no images can see it) will be complete noise, as there's no signal to pick any color or lack of a voxel.

[ Parent | on HN ]

Re:A working implementation of text-to-3D DreamFusion, power... by nobbis on Thursday October 06, 2022 @01:49PM (#33111514)

Yes, although not complete noise – probably empty. Haven't checked but assume there's regularization of the NeRF parameters.

[ Parent | on HN ]

Re:A working implementation of text-to-3D DreamFusion, power... by FeepingCreature on Thursday October 06, 2022 @02:03PM (#33111692)

    text = f"{ref_text}, front cutaway drawing"

Maybe?

[ Parent | on HN ]