3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks

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.

References in corpus (7)

• Spectral Networks and Locally Connected Networks on Graphs
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
• Multi-view Convolutional Neural Networks for 3D Shape Recognition
• Learning shape correspondence with anisotropic convolutional neural networks
• FusionNet: 3D Object Classification Using Multiple Data Representations
• A Point Set Generation Network for 3D Object Reconstruction from a Single Image

Cited by in corpus (7)

• PointCNN: Convolution On $\mathcal{X}$-Transformed Points
• Deep Learning for 3D Point Clouds: A Survey
• Interpolated Convolutional Networks for 3D Point Cloud Understanding
• A survey of Object Classification and Detection based on 2D/3D data
• Efficient Semantic Scene Completion Network with Spatial Group Convolution
• Local-Area-Learning Network: Meaningful Local Areas for Efficient Point Cloud Analysis
• Go Wider: An Efficient Neural Network for Point Cloud Analysis via Group Convolutions