STAGE is a streaming generative world model that generates up to 600-frame driving videos on NuScenes with stable quality, using temporal feature transfer across denoising steps and a multi-stage training schedule.
Vista: A generalizable driving world model with high fidelity and versatile controllability,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation
STAGE is a streaming generative world model that generates up to 600-frame driving videos on NuScenes with stable quality, using temporal feature transfer across denoising steps and a multi-stage training schedule.