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

Yizhak Ben-Shabat, Michael Lindenbaum, Anath Fischer
11/22/2017
cs.CV

Official code: sitzikbs/3DmFV-Net (111 stars, last commit 2019-09-27).

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.

View on arXivView PDF

Code Implementations(1)

sitzikbs/3DmFV-NetOfficial100%

Point cloud classification in Real-time using 3DmFV representation and CNNs

11138C++, CudaJul 2, 20187 years agoNOASSERTION

Similar Papers

Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook

88% match2023

VTPNet for 3D deep learning on point cloud

86% match2023

A Hybrid Generative and Discriminative PointNet on Unordered Point Sets

85% match2024

PointeNet: A Lightweight Framework for Effective and Efficient Point Cloud Analysis

85% match1 repo132023

A Systematic Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation

85% match1 repo62026

Deep Learning for 3D Point Clouds: A Survey

85% match1 repo1.6k2019

Cite this paper

@article{benshabat2017point,
  title  = {3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks},
  author = {Yizhak Ben-Shabat and Michael Lindenbaum and Anath Fischer},
  year   = {2017},
  eprint = {1711.08241},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1711.08241}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1711.08241.svg)](https://codeofpaper.com/paper/1711.08241)

Discussion