Basis point sets encode a point cloud into a fixed-length distance feature, letting a small MLP match PointNet on ModelNet40 with far fewer FLOPs and enabling real-time mesh registration.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Learning on Point Clouds with Basis Point Sets
Basis point sets encode a point cloud into a fixed-length distance feature, letting a small MLP match PointNet on ModelNet40 with far fewer FLOPs and enabling real-time mesh registration.