A diffusion inpainting model conditioned on a second viewpoint of the same scene produces 3D-consistent fills for occluded regions without 3D supervision.
Mitra, and Paul Guer- rero
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
3D-Consistent Image Inpainting with Diffusion Models
A diffusion inpainting model conditioned on a second viewpoint of the same scene produces 3D-consistent fills for occluded regions without 3D supervision.