Weighted multi-projection

3D point cloud denoising with tangent planes

Chaojing Duan, Siheng Chen, Jelena Kovacevic

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

Abstract

We present a novel algorithm for 3D point cloud denoising called weighted multi-projection. As a collection of 3D points sampled from surfaces of objects, a 3D point cloud is widely used in robotics, autonomous driving and augmented reality. Due to the physical limitations of 3D sensing devices, 3D point clouds are usually noisy, which influences subsequent computations. Compared to many previous denoising works, instead of directly smoothing the coordinates of 3D points, we use a two-fold smoothing. We first estimate a local tangent plane at each 3D point and then reconstruct each 3D point by weighted averaging of its projections on multiple tangent planes. We validate the empirical performance on the dataset of ShapeNetCore and show that weighted multi-projection outperforms its competitors in all nine classes.

Original languageEnglish (US)
Title of host publication2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages725-729
Number of pages5
ISBN (Electronic)9781728112954
DOIs
StatePublished - Feb 20 2019
Event2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Anaheim, United States
Duration: Nov 26 2018Nov 29 2018

Publication series

Name2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

Conference

Conference2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018
CountryUnited States
CityAnaheim
Period11/26/1811/29/18

Fingerprint

Augmented reality
Robotics

Keywords

  • 3D point cloud
  • Graph
  • Manifold
  • Surface normal
  • Tangent plane

ASJC Scopus subject areas

  • Information Systems
  • Signal Processing

Cite this

Duan, C., Chen, S., & Kovacevic, J. (2019). Weighted multi-projection: 3D point cloud denoising with tangent planes. In 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings (pp. 725-729). [8646331] (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GlobalSIP.2018.8646331

Weighted multi-projection : 3D point cloud denoising with tangent planes. / Duan, Chaojing; Chen, Siheng; Kovacevic, Jelena.

2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 725-729 8646331 (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings).

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

Duan, C, Chen, S & Kovacevic, J 2019, Weighted multi-projection: 3D point cloud denoising with tangent planes. in 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings., 8646331, 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 725-729, 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018, Anaheim, United States, 11/26/18. https://doi.org/10.1109/GlobalSIP.2018.8646331
Duan C, Chen S, Kovacevic J. Weighted multi-projection: 3D point cloud denoising with tangent planes. In 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 725-729. 8646331. (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings). https://doi.org/10.1109/GlobalSIP.2018.8646331
Duan, Chaojing ; Chen, Siheng ; Kovacevic, Jelena. / Weighted multi-projection : 3D point cloud denoising with tangent planes. 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 725-729 (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings).
@inproceedings{51c1d5033989437792eea2e9a168f4de,
title = "Weighted multi-projection: 3D point cloud denoising with tangent planes",
abstract = "We present a novel algorithm for 3D point cloud denoising called weighted multi-projection. As a collection of 3D points sampled from surfaces of objects, a 3D point cloud is widely used in robotics, autonomous driving and augmented reality. Due to the physical limitations of 3D sensing devices, 3D point clouds are usually noisy, which influences subsequent computations. Compared to many previous denoising works, instead of directly smoothing the coordinates of 3D points, we use a two-fold smoothing. We first estimate a local tangent plane at each 3D point and then reconstruct each 3D point by weighted averaging of its projections on multiple tangent planes. We validate the empirical performance on the dataset of ShapeNetCore and show that weighted multi-projection outperforms its competitors in all nine classes.",
keywords = "3D point cloud, Graph, Manifold, Surface normal, Tangent plane",
author = "Chaojing Duan and Siheng Chen and Jelena Kovacevic",
year = "2019",
month = "2",
day = "20",
doi = "10.1109/GlobalSIP.2018.8646331",
language = "English (US)",
series = "2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "725--729",
booktitle = "2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings",

}

TY - GEN

T1 - Weighted multi-projection

T2 - 3D point cloud denoising with tangent planes

AU - Duan, Chaojing

AU - Chen, Siheng

AU - Kovacevic, Jelena

PY - 2019/2/20

Y1 - 2019/2/20

N2 - We present a novel algorithm for 3D point cloud denoising called weighted multi-projection. As a collection of 3D points sampled from surfaces of objects, a 3D point cloud is widely used in robotics, autonomous driving and augmented reality. Due to the physical limitations of 3D sensing devices, 3D point clouds are usually noisy, which influences subsequent computations. Compared to many previous denoising works, instead of directly smoothing the coordinates of 3D points, we use a two-fold smoothing. We first estimate a local tangent plane at each 3D point and then reconstruct each 3D point by weighted averaging of its projections on multiple tangent planes. We validate the empirical performance on the dataset of ShapeNetCore and show that weighted multi-projection outperforms its competitors in all nine classes.

AB - We present a novel algorithm for 3D point cloud denoising called weighted multi-projection. As a collection of 3D points sampled from surfaces of objects, a 3D point cloud is widely used in robotics, autonomous driving and augmented reality. Due to the physical limitations of 3D sensing devices, 3D point clouds are usually noisy, which influences subsequent computations. Compared to many previous denoising works, instead of directly smoothing the coordinates of 3D points, we use a two-fold smoothing. We first estimate a local tangent plane at each 3D point and then reconstruct each 3D point by weighted averaging of its projections on multiple tangent planes. We validate the empirical performance on the dataset of ShapeNetCore and show that weighted multi-projection outperforms its competitors in all nine classes.

KW - 3D point cloud

KW - Graph

KW - Manifold

KW - Surface normal

KW - Tangent plane

UR - http://www.scopus.com/inward/record.url?scp=85063079670&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063079670&partnerID=8YFLogxK

U2 - 10.1109/GlobalSIP.2018.8646331

DO - 10.1109/GlobalSIP.2018.8646331

M3 - Conference contribution

T3 - 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

SP - 725

EP - 729

BT - 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -