SO-Net: Self-Organizing Network for Point Cloud Analysis

03/12/2018
by   Jiaxin Li, et al.
0

This paper presents SO-Net, a permutation invariant architecture for deep learning with orderless point clouds. The SO-Net models the spatial distribution of point cloud by building a Self-Organizing Map (SOM). Based on the SOM, SO-Net performs hierarchical feature extraction on individual points and SOM nodes, and ultimately represents the input point cloud by a single feature vector. The receptive field of the network can be systematically adjusted by conducting point-to-node k nearest neighbor search. In recognition tasks such as point cloud reconstruction, classification, object part segmentation and shape retrieval, our proposed network demonstrates performance that is similar with or better than state-of-the-art approaches. In addition, the training speed is significantly faster than existing point cloud recognition networks because of the parallelizability and simplicity of the proposed architecture.

READ FULL TEXT

page 4

page 14

page 16

research
03/31/2020

SK-Net: Deep Learning on Point Cloud via End-to-end Discovery of Spatial Keypoints

Since the PointNet was proposed, deep learning on point cloud has been t...
research
04/04/2017

Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models

We present a new deep learning architecture (called Kd-network) that is ...
research
12/11/2018

Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions

Three-dimensional object recognition has recently achieved great progres...
research
05/01/2020

MOPS-Net: A Matrix Optimization-driven Network forTask-Oriented 3D Point Cloud Downsampling

Downsampling is a commonly-used technique in 3D point cloudprocessing fo...
research
06/20/2021

FloorPP-Net: Reconstructing Floor Plans using Point Pillars for Scan-to-BIM

This paper presents a deep learning-based point cloud processing method ...
research
07/20/2023

Variational Point Encoding Deformation for Dental Modeling

Digital dentistry has made significant advancements in recent years, yet...
research
11/22/2021

Point Cloud Color Constancy

In this paper, we present Point Cloud Color Constancy, in short PCCC, an...

Please sign up or login with your details

Forgot password? Click here to reset