Abstract | ||
---|---|---|
We present a novel compact point cloud representation that is inherently invariant to scale, coordinate change and point permutation. The key idea is to parametrize a distance field around an individual shape into a unique, canonical, and compact vector in an unsupervised manner. We firstly project a distance field to a $4$D canonical space using singular value decomposition. We then train a neural network for each instance to non-linearly embed its distance field into network parameters. We employ a bias-free Extreme Learning Machine (ELM) with ReLU activation units, which has scale-factor commutative property between layers. We demonstrate the descriptiveness of the instance-wise, shape-embedded network parameters by using them to classify shapes in $3$D datasets. Our learning-based representation requires minimal augmentation and simple neural networks, where previous approaches demand numerous representations to handle coordinate change and point permutation. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Computer Vision and Pattern Recognition | Singular value decomposition,Pattern recognition,Commutative property,Extreme learning machine,Computer science,Permutation,Algorithm,Distance transform,Invariant (mathematics),Artificial intelligence,Point cloud,Artificial neural network |
DocType | Volume | Citations |
Journal | abs/1809.04820 | 1 |
PageRank | References | Authors |
0.35 | 11 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kent Fujiwara | 1 | 9 | 1.55 |
ikuro sato | 2 | 2 | 1.72 |
Mitsuru Ambai | 3 | 48 | 6.36 |
Yuichi Yoshida | 4 | 469 | 44.88 |
Yoshiaki Sakakura | 5 | 6 | 2.57 |