research-article

3D Point Cloud Denoising Based on Hybrid Attention Mechanism and Score Matching

Authors:

Linyang TianAuthors Info & Claims

AIPR '22: Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition

Pages 767 - 772

https://doi.org/10.1145/3573942.3574093

Published: 16 May 2023 Publication History

Abstract

Due to the limitations of the acquisition equipment, sensors, and the illumination or reflection characteristics of the ground, the acquired point clouds will inevitably be noisy. Noise degrades the quality of point clouds and hinders the subsequent point cloud processing tasks, so the denoising technique becomes a crucial step in point cloud processing. This paper proposes a point cloud denoising algorithm based on a hybrid attention mechanism, which takes into account the complexity of the internal features of point clouds and the randomness of point cloud transformations. Generates channel and spatial attention by parallel maximum pooling and average pooling of point cloud data, trains adaptive attention weights using a multilayer perceptron with shared weights, and serially fuses them, multiplies them with the input features to obtain more robust point cloud features, and connect to the score estimation module using the residuals. By studying and analyzing the mechanism proposed in this paper, it is experimentally demonstrated that the performance of the proposed model under various noise models is vastly improved over the baseline network and outperforms the advanced denoising methods without significantly increasing the network operation cost.

References

[1]

Yang Peng, Liu de'er, Liu Jing Yu, Urban point cloud denoising algorithm based on least square density clustering [J] Laser and infrared, 2020, 50 (11): 1402-1409

[2]

Wei Shuo, Zhao Nanxiang, Li Minle, A single photon denoising algorithm combining improved DBSCAN and statistical filtering [J] Laser technology, 2021, 45 (5): 601

[3]

Mattei, E. and Castrodad, A. (2017), Point Cloud Denoising via Moving RPCA. Computer Graphics Forum, 36: 123-137. https://doi.org/10.1111/cgf.13068

[4]

Schoenenberger Y, Paratte J, Vandergheynst P. Graph-based denoising for time-varying point clouds[C]//2015 3DTV-Conference: The True Vision-Capture, Transmission and Display of 3D Video (3DTV-CON). IEEE, 2015: 1-4.

[5]

Zeng J, Cheung G, Ng M, 3D point cloud denoising using graph Laplacian regularization of a low dimensional manifold model[J]. IEEE Transactions on Image Processing, 2019, 29: 3474-3489.

Digital Library

[6]

Hu W, Gao X, Cheung G, Feature graph learning for 3D point cloud denoising[J]. IEEE Transactions on Signal Processing, 2020, 68: 2841-2856.

[7]

Hu W, Pang J, Liu X, Graph signal processing for geometric data and beyond: Theory and applications[J]. IEEE Transactions on Multimedia, 2021.

[8]

Sun Y, Schaefer S, Wang W. Denoising point sets via L0 minimization[J]. Computer Aided Geometric Design, 2015, 35: 2-15.

Digital Library

[9]

Xu L, Wang R, Zhang J, Survey on sparsity in geometric modeling and processing[J]. Graphical Models, 2015, 82:160-180.

Digital Library

[10]

Qi C R, Su H, Mo K, Pointnet: Deep learning on point sets for 3d classification and segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 652-660.

[11]

Duan C, Chen S, Kovacevic J. 3D point cloud denoising via deep neural network based local surface estimation[C]//ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) IEEE, 2019: 8553-8557

[12]

Zhou H, Chen K, Zhang W, Dup-net: Denoiser and upsampler network for 3d adversarial point clouds defense[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019: 1961-1970.

[13]

Rakotosaona M J, La Barbera V, Guerrero P, Pointcleannet: Learning to denoise and remove outliers from dense point clouds[C]//Computer Graphics Forum. 2020, 39(1): 185-203.

[14]

Hermosilla P, Ritschel T, Ropinski T. Total denoising: Unsupervised learning of 3d point cloud cleaning[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2019: 52-60.

[15]

Luo S, Hu W. Differentiable manifold reconstruction for point cloud denoising[C]//Proceedings of the 28th ACM international conference on multimedia. 2020: 1330-1338.

[16]

Luo S, Hu W. Score-based point cloud denoising[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 4583-4592.

[17]

Yifan W, Wu S, Huang H, Patch-based progressive 3d point set upsampling[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 5958-5967.

[18]

Li R, Li X, Fu C W, Pu-gan: a point cloud upsampling adversarial network[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2019: 7203-7212.

[19]

Huang G, Liu Z, Van Der Maaten L, Densely connected convolutional networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4700-4708.

[20]

Shen Y, Feng C, Yang Y, Mining point cloud local structures by kernel correlation and graph pooling[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4548-4557.

[21]

Liu Y, Fan B, Meng G, Densepoint: Learning densely contextual representation for efficient point cloud processing[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2019: 5239-5248.

[22]

Cai R, Yang G, Averbuch-Elor H, Learning gradient fields for shape generation[C]//European Conference on Computer Vision. Springer, Cham, 2020: 364-381.

[23]

Woo S, Park J, Lee J Y, Cbam: Convolutional block attention module[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 3-19.

[24]

Yu L, Li X, Fu C W, Pu-net: Point cloud upsampling network[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 2790-2799.

[25]

Gschwandtner M, Kwitt R, Uhl A, BlenSor: Blender sensor simulation toolbox[C]//International Symposium on Visual Computing. Springer, Berlin, Heidelberg, 2011: 199-208.

Cited By

Wu JXiang LYou HTang LGai J(2024)Plant-Denoising-Net (PDN): A plant point cloud denoising network based on density gradient field learningISPRS Journal of Photogrammetry and Remote Sensing10.1016/j.isprsjprs.2024.03.010210(282-299)Online publication date: Apr-2024
https://doi.org/10.1016/j.isprsjprs.2024.03.010

Index Terms

3D Point Cloud Denoising Based on Hybrid Attention Mechanism and Score Matching
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision tasks
        Scene anomaly detection

Recommendations

Wiener Filter-Based Point Cloud Adaptive Denoising for Video-based Point Cloud Compression
APCCPA '22: Proceedings of the 1st International Workshop on Advances in Point Cloud Compression, Processing and Analysis

We propose a Wiener filter-based point cloud adaptive denoising method for video-based point cloud compression (V-PCC) platform. The proposed Wiener filter is conducted for two dimension (2D) geometry images generated by V-PCC platform. Due to the large ...
A single-stage point cloud cleaning network for outlier removal and denoising
Highlights
- A novel neural network that can effectively remove outliers and noisy points.
- ...
Abstract
As a simple, flexible and effective representation for objects, 3D point cloud has attracted more and more attention in recent years. However, raw point clouds obtained from 3D scanners or image-based reconstruction techniques are ...
Image Denoising Algorithms: A Comparative Study of Different Filtration Approaches Used in Image Restoration
CSNT '13: Proceedings of the 2013 International Conference on Communication Systems and Network Technologies

To send visual digital images is a major issue in the modern data communication network. The image sent from sender end may not be the same at the receiving end. The image obtained after transmission is often corrupted with noise. The image received at ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

AIPR '22: Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition

September 2022

1221 pages

ISBN:9781450396899

DOI:10.1145/3573942

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 16 May 2023

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

AIPR 2022

AIPR 2022: 2022 5th International Conference on Artificial Intelligence and Pattern Recognition

September 23 - 25, 2022

Xiamen, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
64
Total Downloads

Downloads (Last 12 months)23
Downloads (Last 6 weeks)4

Reflects downloads up to 01 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Wu JXiang LYou HTang LGai J(2024)Plant-Denoising-Net (PDN): A plant point cloud denoising network based on density gradient field learningISPRS Journal of Photogrammetry and Remote Sensing10.1016/j.isprsjprs.2024.03.010210(282-299)Online publication date: Apr-2024
https://doi.org/10.1016/j.isprsjprs.2024.03.010

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Figures

Tables

Media

View Table of Conten