3D Point Cloud Denoising via Deep Neural Network Based Local Surface Estimation

Chaojing Duan, Siheng Chen, Jelena Kovacevic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a neural-network-based architecture for 3D point cloud denoising called neural projection denoising (NPD). In our previous work, we proposed a two-stage denoising algorithm, which first estimates reference planes and follows by projecting noisy points to estimated reference planes. Since the estimated reference planes are inevitably noisy, multi-projection is applied to stabilize the denoising performance. NPD algorithm uses a neural network to estimate reference planes for points in noisy point clouds. With more accurate estimations of reference planes, we are able to achieve better denoising performances with only one-time projection. To the best of our knowledge, NPD is the first work to denoise 3D point clouds with deep learning techniques. To conduct the experiments, we sample 40000 point clouds from the 3D data in ShapeNet to train a network and sample 350 point clouds from the 3D data in ModelNet10 to test. Experimental results show that our algorithm can estimate normal vectors of points in noisy point clouds. Comparing to five competitive methods, the proposed algorithm achieves better denoising performance and produces much smaller variances. Our code is available at https://github.com/chaojingduan/Neural-Projection.

Original languageEnglish (US)
Title of host publication2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages8553-8557
Number of pages5
ISBN (Electronic)9781479981311
DOIs
StatePublished - May 1 2019
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: May 12 2019May 17 2019

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May
ISSN (Print)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom
CityBrighton
Period5/12/195/17/19

Fingerprint

Neural networks
Deep neural networks
Experiments
Deep learning

Keywords

  • deep learning
  • denoising
  • normal vector
  • point cloud
  • reference plane

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Duan, C., Chen, S., & Kovacevic, J. (2019). 3D Point Cloud Denoising via Deep Neural Network Based Local Surface Estimation. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 8553-8557). [8682812] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2019.8682812

3D Point Cloud Denoising via Deep Neural Network Based Local Surface Estimation. / Duan, Chaojing; Chen, Siheng; Kovacevic, Jelena.

2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 8553-8557 8682812 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Duan, C, Chen, S & Kovacevic, J 2019, 3D Point Cloud Denoising via Deep Neural Network Based Local Surface Estimation. in 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings., 8682812, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 8553-8557, 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, Brighton, United Kingdom, 5/12/19. https://doi.org/10.1109/ICASSP.2019.8682812
Duan C, Chen S, Kovacevic J. 3D Point Cloud Denoising via Deep Neural Network Based Local Surface Estimation. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 8553-8557. 8682812. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2019.8682812
Duan, Chaojing ; Chen, Siheng ; Kovacevic, Jelena. / 3D Point Cloud Denoising via Deep Neural Network Based Local Surface Estimation. 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 8553-8557 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{afbc7869c7fc492c8d8a8936e30eb912,
title = "3D Point Cloud Denoising via Deep Neural Network Based Local Surface Estimation",
abstract = "We present a neural-network-based architecture for 3D point cloud denoising called neural projection denoising (NPD). In our previous work, we proposed a two-stage denoising algorithm, which first estimates reference planes and follows by projecting noisy points to estimated reference planes. Since the estimated reference planes are inevitably noisy, multi-projection is applied to stabilize the denoising performance. NPD algorithm uses a neural network to estimate reference planes for points in noisy point clouds. With more accurate estimations of reference planes, we are able to achieve better denoising performances with only one-time projection. To the best of our knowledge, NPD is the first work to denoise 3D point clouds with deep learning techniques. To conduct the experiments, we sample 40000 point clouds from the 3D data in ShapeNet to train a network and sample 350 point clouds from the 3D data in ModelNet10 to test. Experimental results show that our algorithm can estimate normal vectors of points in noisy point clouds. Comparing to five competitive methods, the proposed algorithm achieves better denoising performance and produces much smaller variances. Our code is available at https://github.com/chaojingduan/Neural-Projection.",
keywords = "deep learning, denoising, normal vector, point cloud, reference plane",
author = "Chaojing Duan and Siheng Chen and Jelena Kovacevic",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/ICASSP.2019.8682812",
language = "English (US)",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "8553--8557",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",

}

TY - GEN

T1 - 3D Point Cloud Denoising via Deep Neural Network Based Local Surface Estimation

AU - Duan, Chaojing

AU - Chen, Siheng

AU - Kovacevic, Jelena

PY - 2019/5/1

Y1 - 2019/5/1

N2 - We present a neural-network-based architecture for 3D point cloud denoising called neural projection denoising (NPD). In our previous work, we proposed a two-stage denoising algorithm, which first estimates reference planes and follows by projecting noisy points to estimated reference planes. Since the estimated reference planes are inevitably noisy, multi-projection is applied to stabilize the denoising performance. NPD algorithm uses a neural network to estimate reference planes for points in noisy point clouds. With more accurate estimations of reference planes, we are able to achieve better denoising performances with only one-time projection. To the best of our knowledge, NPD is the first work to denoise 3D point clouds with deep learning techniques. To conduct the experiments, we sample 40000 point clouds from the 3D data in ShapeNet to train a network and sample 350 point clouds from the 3D data in ModelNet10 to test. Experimental results show that our algorithm can estimate normal vectors of points in noisy point clouds. Comparing to five competitive methods, the proposed algorithm achieves better denoising performance and produces much smaller variances. Our code is available at https://github.com/chaojingduan/Neural-Projection.

AB - We present a neural-network-based architecture for 3D point cloud denoising called neural projection denoising (NPD). In our previous work, we proposed a two-stage denoising algorithm, which first estimates reference planes and follows by projecting noisy points to estimated reference planes. Since the estimated reference planes are inevitably noisy, multi-projection is applied to stabilize the denoising performance. NPD algorithm uses a neural network to estimate reference planes for points in noisy point clouds. With more accurate estimations of reference planes, we are able to achieve better denoising performances with only one-time projection. To the best of our knowledge, NPD is the first work to denoise 3D point clouds with deep learning techniques. To conduct the experiments, we sample 40000 point clouds from the 3D data in ShapeNet to train a network and sample 350 point clouds from the 3D data in ModelNet10 to test. Experimental results show that our algorithm can estimate normal vectors of points in noisy point clouds. Comparing to five competitive methods, the proposed algorithm achieves better denoising performance and produces much smaller variances. Our code is available at https://github.com/chaojingduan/Neural-Projection.

KW - deep learning

KW - denoising

KW - normal vector

KW - point cloud

KW - reference plane

UR - http://www.scopus.com/inward/record.url?scp=85068961347&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068961347&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2019.8682812

DO - 10.1109/ICASSP.2019.8682812

M3 - Conference contribution

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 8553

EP - 8557

BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -