SynFlow creates a 34-times larger synthetic LiDAR scene flow dataset that lets models trained only on simulation match or beat supervised real-data baselines on multiple benchmarks.
In: Proceedings of the Computer Vision and Pattern Recognition Con- ference
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
-
SynFlow: Scaling Up LiDAR Scene Flow Estimation with Synthetic Data
SynFlow creates a 34-times larger synthetic LiDAR scene flow dataset that lets models trained only on simulation match or beat supervised real-data baselines on multiple benchmarks.