Satellite-to-ground generation is extended from single images to consistent multi-view sequences by adding satellite-guided and satellite-temporal conditioning to a frozen latent diffusion model, with a new 100k-pair dataset.
Scenescape: text-driven consistent scene generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Satellite to GroundScape -- Large-scale Consistent Ground View Generation from Satellite Views
Satellite-to-ground generation is extended from single images to consistent multi-view sequences by adding satellite-guided and satellite-temporal conditioning to a frozen latent diffusion model, with a new 100k-pair dataset.