BEV-VAE encodes multi-view driving images into one BEV latent, then applies a latent diffusion transformer to generate novel, layout-controllable surround-view images.
Driving into the future: Multiview visual forecasting and planning with world model for autonomous driving
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
-
BEV-VAE: Multi-view Image Generation with Spatial Consistency for Autonomous Driving
BEV-VAE encodes multi-view driving images into one BEV latent, then applies a latent diffusion transformer to generate novel, layout-controllable surround-view images.