OVIE trains monocular novel view synthesis on unpaired images using depth-based pseudo-views and masked losses, outperforming priors in zero-shot settings while being 600x faster.
In: CVPR (2021) 8, 25
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
One View Is Enough! Monocular Training for In-the-Wild Novel View Generation
OVIE trains monocular novel view synthesis on unpaired images using depth-based pseudo-views and masked losses, outperforming priors in zero-shot settings while being 600x faster.