Re:Localrf – Nerf from casual shaky videos
by v7n on Friday June 16, 2023 @05:03AM
(#36353578)
Let's say you want to slightly alter the spline the camera of the 3D scene moves along, but the positions/angles would change in such a way there is missing data in the new rendering. How feasible would it be to use current inpainting technologies to fill in the gaps straight in the scene? Would it be better to try to inpaint the rendered frames instead?
[ Parent
| on HN ]
Re:Localrf – Nerf from casual shaky videos
by david24802 on Friday June 16, 2023 @10:41AM
(#36357305)
You may be interested in GeNVS (https://nvlabs.github.io/genvs/) which combines NeRFs and generative diffusion models.