A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sarker, Sushmita, Sarker, Prithul, Stone, Gunner, Gorman, Ryan, Tavakkoli, Alireza, Bebis, George, Sattarvand, Javad
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914802758057984
author Sarker, Sushmita
Sarker, Prithul
Stone, Gunner
Gorman, Ryan
Tavakkoli, Alireza
Bebis, George
Sattarvand, Javad
author_facet Sarker, Sushmita
Sarker, Prithul
Stone, Gunner
Gorman, Ryan
Tavakkoli, Alireza
Bebis, George
Sattarvand, Javad
contents Point cloud analysis has a wide range of applications in many areas such as computer vision, robotic manipulation, and autonomous driving. While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unordered, irregular and noisy 3D points. To stimulate future research, this paper analyzes recent progress in deep learning methods employed for point cloud processing and presents challenges and potential directions to advance this field. It serves as a comprehensive review on two major tasks in 3D point cloud processing-- namely, 3D shape classification and semantic segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11903
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation
Sarker, Sushmita
Sarker, Prithul
Stone, Gunner
Gorman, Ryan
Tavakkoli, Alireza
Bebis, George
Sattarvand, Javad
Computer Vision and Pattern Recognition
Point cloud analysis has a wide range of applications in many areas such as computer vision, robotic manipulation, and autonomous driving. While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unordered, irregular and noisy 3D points. To stimulate future research, this paper analyzes recent progress in deep learning methods employed for point cloud processing and presents challenges and potential directions to advance this field. It serves as a comprehensive review on two major tasks in 3D point cloud processing-- namely, 3D shape classification and semantic segmentation.
title A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.11903