A feed-forward Transformer turns sparse multi-view video frames into 3D Gaussians with velocities, reconstructing dynamic driving scenes in 0.2 seconds and estimating scene flow without motion labels.
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
-
STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
A feed-forward Transformer turns sparse multi-view video frames into 3D Gaussians with velocities, reconstructing dynamic driving scenes in 0.2 seconds and estimating scene flow without motion labels.