3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks
Published in
arXiv.org(2017)External Links:
TL
TL;DR
A novel 3D point cloud representation called 3D Modified Fisher Vectors (3DmFV) is proposed, which combines the discrete structure of a grid with continuous generalization of Fisher vectors, in a compact and computationally efficient way.
Abstract
The point cloud is gaining prominence as a method for representing 3D shapes, but its irregular format poses a challenge for deep learning methods. The common solution of transforming the data into a 3D voxel grid introduces its own challenges, mainly large memory size. In this paper we propose a novel 3D point cloud representation called 3D Modified Fisher Vectors (3DmFV). Our representation is hybrid as it combines the discrete structure of a grid with continuous generalization of Fisher vectors, in a compact and computationally efficient way. Using the grid enables us to design a new CNN architecture for point cloud classification and part segmentation. In a series of experiments we demonstrate competitive performance or even better than state-of-the-art on challenging benchmark datasets.
References36 items
1
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
2
Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models
3
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
4
A Point Set Generation Network for 3D Object Reconstruction from a Single Image
5