A diffusion model trained on 1 million 360-degree videos synthesizes novel views with camera translation and enables 3D reconstruction from a single image.
Title resolution pending
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
-
From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos
A diffusion model trained on 1 million 360-degree videos synthesizes novel views with camera translation and enables 3D reconstruction from a single image.