Deep-Learning-Based 3-D Surface Reconstruction-A Survey

In the last decade, deep learning (DL) has significantly impacted industry and science. Initially largely motivated by computer vision tasks in 2-D imagery, the focus has shifted toward 3-D data analysis. In particular, 3-D surface reconstruction, i.e., reconstructing a 3-D shape from sparse input,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the IEEE Jg. 111; H. 11; S. 1464 - 1501
Hauptverfasser: Farshian, Anis, Gotz, Markus, Cavallaro, Gabriele, Debus, Charlotte, Niesner, Matthias, Benediktsson, Jon Atli, Streit, Achim
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.11.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
3-D deep learning (DL)
3-D surface reconstruction
Computer vision
Data analysis
Deep learning
Geometric algorithms
geometric DL
Geometric modeling
geometry processing
Image acquisition
Image reconstruction
Laser radar
Machine learning
Point cloud compression
Surface emitting lasers
Surface reconstruction
Surveys
Taxonomy
Three-dimensional displays
ISSN:0018-9219, 1558-2256
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In the last decade, deep learning (DL) has significantly impacted industry and science. Initially largely motivated by computer vision tasks in 2-D imagery, the focus has shifted toward 3-D data analysis. In particular, 3-D surface reconstruction, i.e., reconstructing a 3-D shape from sparse input, is of great interest to a large variety of application fields. DL-based approaches show promising quantitative and qualitative surface reconstruction performance compared to traditional computer vision and geometric algorithms. This survey provides a comprehensive overview of these DL-based methods for 3-D surface reconstruction. To this end, we will first discuss input data modalities, such as volumetric data, point clouds, and RGB, single-view, multiview, and depth images, along with corresponding acquisition technologies and common benchmark datasets. For practical purposes, we also discuss evaluation metrics enabling us to judge the reconstructive performance of different methods. The main part of the document will introduce a methodological taxonomy ranging from point- and mesh-based techniques to volumetric and implicit neural approaches. Recent research trends, both methodological and for applications, are highlighted, pointing toward future developments.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9219
1558-2256
DOI:10.1109/JPROC.2023.3321433