Local learning in point clouds based on spectral pooling

Yushi Li, George Baciu

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

As one of the most fundamental geometric data types for the representation of space and object shapes, a point cloud usually maintains much structural information about the spatial relationship between objects and their features. However, the relative sparseness of point clouds sampled in most practical applications make extracting information-rich features a major challenge. Traditionally, feature extraction algorithms resorted to structured feature engineering and used handcrafted representations for some specific problems. Motivated by the development of deep neural networks, many researchers started to handle the unstructured point clouds from the raw data samples of 3D scanning devices. Some important advantages that deep learning frameworks have over traditional feature engineering is generalizing complex features and associated semantic concepts in a hierarchical manner. Deep learning models have achieved significant landmarks in cognitive processing of speech, image, and video signals. However, unlike in 2D image processing, a 3D point cloud is irregular and sparse. Hence, traditional network frameworks are difficult to apply on 3D geometric data directly. In this paper, we propose to integrate a local point convolution network with spectral pooling to aggregate and learn features in 3D point clouds. The benefits of our framework are fast convergence and competitive performance on point cloud classification.

Original languageEnglish
Title of host publicationProceedings of 2020 IEEE 19th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2020
EditorsYingxu Wang, Ning Ge, Jianhua Lu, Xiaoming Tao, Paolo Soda, Newton Howard, Bernard Widrow, Jerome Feldman
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages84-91
Number of pages8
ISBN (Electronic)9781728195940
DOIs
Publication statusPublished - 26 Sept 2020
Externally publishedYes
Event19th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2020 - Beijing, China
Duration: 26 Sept 202028 Sept 2020

Publication series

NameProceedings of 2020 IEEE 19th International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2020

Conference

Conference19th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2020
Country/TerritoryChina
CityBeijing
Period26/09/2028/09/20

Cite this