A new point cloud convolution that interpolates features to fixed discrete kernel weights with density normalization achieves state-of-the-art on ModelNet40, ShapeNet Parts, and S3DIS.
3dcapsule: Extending the capsule architecture to classify 3d point clouds
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
-
Interpolated Convolutional Networks for 3D Point Cloud Understanding
A new point cloud convolution that interpolates features to fixed discrete kernel weights with density normalization achieves state-of-the-art on ModelNet40, ShapeNet Parts, and S3DIS.