TOWARD UNSUPERVISED 3D POINT CLOUD ANOMALY DETECTION USING VARIATIONAL AUTOENCODER

Mana Masuda; Ryo Hachiuma; Ryo Fujii; Hideo Saito; Yusuke Sekikawa

doi:10.1109/ICIP42928.2021.9506795

TOWARD UNSUPERVISED 3D POINT CLOUD ANOMALY DETECTION USING VARIATIONAL AUTOENCODER

Mana Masuda, Ryo Hachiuma, Ryo Fujii, Hideo Saito, Yusuke Sekikawa

Department of Information and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

In this paper, we present an end-to-end unsupervised anomaly detection framework for 3D point clouds. To the best of our knowledge, this is the first work to tackle the anomaly detection task on a general object represented by a 3D point cloud. We propose a deep variational autoencoder based unsupervised anomaly detection network adapted to the 3D point cloud and an anomaly score specifically for 3D point clouds. To verify the effectiveness of the model, we conducted extensive experiments on ShapeNet dataset. Through quantitative and qualitative evaluation, we demonstrate that the proposed method outperforms the baseline method.

Original language	English
Title of host publication	2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
Publisher	IEEE Computer Society
Pages	3118-3122
Number of pages	5
ISBN (Electronic)	9781665441155
DOIs	https://doi.org/10.1109/ICIP42928.2021.9506795
Publication status	Published - 2021
Event	2021 IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States Duration: 2021 Sep 19 → 2021 Sep 22

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2021-September
ISSN (Print)	1522-4880

Conference

Conference	2021 IEEE International Conference on Image Processing, ICIP 2021
Country/Territory	United States
City	Anchorage
Period	21/9/19 → 21/9/22

Keywords

3D point cloud
Anomaly detection
Unsupervised learning
Variational autoencoder

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP42928.2021.9506795

Cite this

Masuda, M., Hachiuma, R., Fujii, R., Saito, H., & Sekikawa, Y. (2021). TOWARD UNSUPERVISED 3D POINT CLOUD ANOMALY DETECTION USING VARIATIONAL AUTOENCODER. In 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings (pp. 3118-3122). (Proceedings - International Conference on Image Processing, ICIP; Vol. 2021-September). IEEE Computer Society. https://doi.org/10.1109/ICIP42928.2021.9506795

TOWARD UNSUPERVISED 3D POINT CLOUD ANOMALY DETECTION USING VARIATIONAL AUTOENCODER. / Masuda, Mana; Hachiuma, Ryo; Fujii, Ryo et al.

2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings. IEEE Computer Society, 2021. p. 3118-3122 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2021-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Masuda, M, Hachiuma, R, Fujii, R, Saito, H & Sekikawa, Y 2021, TOWARD UNSUPERVISED 3D POINT CLOUD ANOMALY DETECTION USING VARIATIONAL AUTOENCODER. in 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, vol. 2021-September, IEEE Computer Society, pp. 3118-3122, 2021 IEEE International Conference on Image Processing, ICIP 2021, Anchorage, United States, 21/9/19. https://doi.org/10.1109/ICIP42928.2021.9506795

@inproceedings{a7468c3c18544e5ea52e8526b4554765,

title = "TOWARD UNSUPERVISED 3D POINT CLOUD ANOMALY DETECTION USING VARIATIONAL AUTOENCODER",

abstract = "In this paper, we present an end-to-end unsupervised anomaly detection framework for 3D point clouds. To the best of our knowledge, this is the first work to tackle the anomaly detection task on a general object represented by a 3D point cloud. We propose a deep variational autoencoder based unsupervised anomaly detection network adapted to the 3D point cloud and an anomaly score specifically for 3D point clouds. To verify the effectiveness of the model, we conducted extensive experiments on ShapeNet dataset. Through quantitative and qualitative evaluation, we demonstrate that the proposed method outperforms the baseline method.",

keywords = "3D point cloud, Anomaly detection, Unsupervised learning, Variational autoencoder",

author = "Mana Masuda and Ryo Hachiuma and Ryo Fujii and Hideo Saito and Yusuke Sekikawa",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Conference on Image Processing, ICIP 2021 ; Conference date: 19-09-2021 Through 22-09-2021",

year = "2021",

doi = "10.1109/ICIP42928.2021.9506795",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "3118--3122",

booktitle = "2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings",

}

TY - GEN

T1 - TOWARD UNSUPERVISED 3D POINT CLOUD ANOMALY DETECTION USING VARIATIONAL AUTOENCODER

AU - Masuda, Mana

AU - Hachiuma, Ryo

AU - Fujii, Ryo

AU - Saito, Hideo

AU - Sekikawa, Yusuke

PY - 2021

Y1 - 2021

N2 - In this paper, we present an end-to-end unsupervised anomaly detection framework for 3D point clouds. To the best of our knowledge, this is the first work to tackle the anomaly detection task on a general object represented by a 3D point cloud. We propose a deep variational autoencoder based unsupervised anomaly detection network adapted to the 3D point cloud and an anomaly score specifically for 3D point clouds. To verify the effectiveness of the model, we conducted extensive experiments on ShapeNet dataset. Through quantitative and qualitative evaluation, we demonstrate that the proposed method outperforms the baseline method.

AB - In this paper, we present an end-to-end unsupervised anomaly detection framework for 3D point clouds. To the best of our knowledge, this is the first work to tackle the anomaly detection task on a general object represented by a 3D point cloud. We propose a deep variational autoencoder based unsupervised anomaly detection network adapted to the 3D point cloud and an anomaly score specifically for 3D point clouds. To verify the effectiveness of the model, we conducted extensive experiments on ShapeNet dataset. Through quantitative and qualitative evaluation, we demonstrate that the proposed method outperforms the baseline method.

KW - 3D point cloud

KW - Anomaly detection

KW - Unsupervised learning

KW - Variational autoencoder

UR - http://www.scopus.com/inward/record.url?scp=85125560969&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85125560969&partnerID=8YFLogxK

U2 - 10.1109/ICIP42928.2021.9506795

DO - 10.1109/ICIP42928.2021.9506795

M3 - Conference contribution

AN - SCOPUS:85125560969

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 3118

EP - 3122

BT - 2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings

PB - IEEE Computer Society

T2 - 2021 IEEE International Conference on Image Processing, ICIP 2021

Y2 - 19 September 2021 through 22 September 2021

ER -

TOWARD UNSUPERVISED 3D POINT CLOUD ANOMALY DETECTION USING VARIATIONAL AUTOENCODER

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this