Starting flow-matching video generation from a depth-warped reference frame with spatially-adaptive noise injection reduces required sampling steps by about five times on NuScenes driving videos.
In: Proceedings of the IEEE/CVF International Conference on Computer Vision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors
Starting flow-matching video generation from a depth-warped reference frame with spatially-adaptive noise injection reduces required sampling steps by about five times on NuScenes driving videos.