LGS learns where to prune and add Gaussian primitives in feed-forward driving reconstruction using gradient-response interventions, and aggregates cross-time features, improving novel-view synthesis on Waymo and PandaSet.
Proceedings of the Computer Vision and Pattern Recognition Conference , pages=
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
-
Learning Gaussian Structure: Intervention-Guided Density Control for Feed-Forward Driving Reconstruction
LGS learns where to prune and add Gaussian primitives in feed-forward driving reconstruction using gradient-response interventions, and aggregates cross-time features, improving novel-view synthesis on Waymo and PandaSet.