Deep Learning on 3D Semantic Segmentation: A Detailed Review

In this paper, an exhaustive review and comprehensive analysis of recent and former deep learning methods in 3D semantic segmentation (3DSS) is presented. In the related literature, the taxonomy scheme used for the classification of 3DSS deep learning methods is ambiguous. Based on the taxonomy sche...

Full description

Saved in:
Bibliographic Details
Main Authors: Thodoris Betsas, Andreas Georgopoulos, Anastasios Doulamis, Pierre Grussenmeyer
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/2/298
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832587609607503872
author Thodoris Betsas
Andreas Georgopoulos
Anastasios Doulamis
Pierre Grussenmeyer
author_facet Thodoris Betsas
Andreas Georgopoulos
Anastasios Doulamis
Pierre Grussenmeyer
author_sort Thodoris Betsas
collection DOAJ
description In this paper, an exhaustive review and comprehensive analysis of recent and former deep learning methods in 3D semantic segmentation (3DSS) is presented. In the related literature, the taxonomy scheme used for the classification of 3DSS deep learning methods is ambiguous. Based on the taxonomy schemes of nine existing review papers, a new taxonomy scheme for 3DSS deep learning methods is proposed, aiming to standardize it and improve the comparability and clarity across related studies. Furthermore, an extensive overview of the available 3DSS indoor and outdoor datasets is provided along with their links. The core part of this review is the detailed presentation of recent and former 3DSS deep learning methods and their classification using the proposed taxonomy scheme along with their GitHub repositories. Additionally, a brief but informative analysis of the evaluation metrics and loss functions used in 3DSS is included. Finally, a fruitful discussion of the examined 3DSS methods and datasets is presented to foster new research directions and applications in the field of 3DSS. In addition to this review, a GitHub repository is provided, including an initial classification of over 400 3DSS methods, using the proposed taxonomy scheme.
format Article
id doaj-art-f4d530b24abb41ceb758ca44397652ff
institution Kabale University
issn 2072-4292
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-f4d530b24abb41ceb758ca44397652ff2025-01-24T13:48:02ZengMDPI AGRemote Sensing2072-42922025-01-0117229810.3390/rs17020298Deep Learning on 3D Semantic Segmentation: A Detailed ReviewThodoris Betsas0Andreas Georgopoulos1Anastasios Doulamis2Pierre Grussenmeyer3Laboratory of Photogrammetry, School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, 15772 Athens, GreeceLaboratory of Photogrammetry, School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, 15772 Athens, GreeceLaboratory of Photogrammetry, School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, 15772 Athens, GreeceICube Laboratory UMR 7357, CNRS, INSA Strasbourg, Université de Strasbourg, 67084 Strasbourg, FranceIn this paper, an exhaustive review and comprehensive analysis of recent and former deep learning methods in 3D semantic segmentation (3DSS) is presented. In the related literature, the taxonomy scheme used for the classification of 3DSS deep learning methods is ambiguous. Based on the taxonomy schemes of nine existing review papers, a new taxonomy scheme for 3DSS deep learning methods is proposed, aiming to standardize it and improve the comparability and clarity across related studies. Furthermore, an extensive overview of the available 3DSS indoor and outdoor datasets is provided along with their links. The core part of this review is the detailed presentation of recent and former 3DSS deep learning methods and their classification using the proposed taxonomy scheme along with their GitHub repositories. Additionally, a brief but informative analysis of the evaluation metrics and loss functions used in 3DSS is included. Finally, a fruitful discussion of the examined 3DSS methods and datasets is presented to foster new research directions and applications in the field of 3DSS. In addition to this review, a GitHub repository is provided, including an initial classification of over 400 3DSS methods, using the proposed taxonomy scheme.https://www.mdpi.com/2072-4292/17/2/2983D semantic segmentationpoint cloudsdeep learningreview
spellingShingle Thodoris Betsas
Andreas Georgopoulos
Anastasios Doulamis
Pierre Grussenmeyer
Deep Learning on 3D Semantic Segmentation: A Detailed Review
Remote Sensing
3D semantic segmentation
point clouds
deep learning
review
title Deep Learning on 3D Semantic Segmentation: A Detailed Review
title_full Deep Learning on 3D Semantic Segmentation: A Detailed Review
title_fullStr Deep Learning on 3D Semantic Segmentation: A Detailed Review
title_full_unstemmed Deep Learning on 3D Semantic Segmentation: A Detailed Review
title_short Deep Learning on 3D Semantic Segmentation: A Detailed Review
title_sort deep learning on 3d semantic segmentation a detailed review
topic 3D semantic segmentation
point clouds
deep learning
review
url https://www.mdpi.com/2072-4292/17/2/298
work_keys_str_mv AT thodorisbetsas deeplearningon3dsemanticsegmentationadetailedreview
AT andreasgeorgopoulos deeplearningon3dsemanticsegmentationadetailedreview
AT anastasiosdoulamis deeplearningon3dsemanticsegmentationadetailedreview
AT pierregrussenmeyer deeplearningon3dsemanticsegmentationadetailedreview