[2016]PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

[YoshiProton]

[Title] PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
[Authors] Charles R. Qi, Hao Su, Kaichun Mo, Leonidas J. Guibas
(Submitted on 2 Dec 2016 (v1), last revised 10 Apr 2017 (this version, v2))
[ArXiv] arXiv:1612.00593 [cs.CV]

Point cloud is an important type of geometric data structure.
Due to its irregular format, most researchers transform such data to regular
3D voxel grids or collections of images.
This, however, renders data unnecessarily voluminous and causes issues.
In this paper, we design a novel type of neural network that directly consumes point clouds
and well respects the permutation invariance of points in the input.
Our network, named PointNet, provides a unified architecture for applications ranging
from object classification, part segmentation, to scene semantic parsing.
Though simple, PointNet is highly efficient and effective.
Empirically, it shows strong performance on par or even better than state of the art.
Theoretically, we provide analysis towards understanding of what the network has learnt
and why the network is robust with respect to input perturbation and corruption.