skip to main content
10.1145/3622896.3622915acmotherconferencesArticle/Chapter ViewAbstractPublication PagesccrisConference Proceedingsconference-collections
research-article

PointWave-MLP: Point Cloud Analysis Based on Wave-MLP Architecture

Published: 03 October 2023 Publication History

Abstract

Due to the irregularity and disorder of point clouds, point cloud analysis based on deep learning remains a challenging task. Although the previous point cloud analysis networks based on multi-layer perceptions (MLPs) exhibit a simple structure, they fail to consider semantic information among different tokens by exploiting fully connected layers with fixed weights for token aggregation. To address this limitation, we draw inspiration from the Wave-MLP architecture in the 2D image field and introduce the concept of phase-aware token mixing into 3D point cloud processing, aiming to dynamically adjust the relationship between tokens and the fixed weights. In this paper, we propose a novel point cloud analysis network called PointWave-MLP. Experimental results demonstrate that PointWave-MLP achieves significant improvements in point cloud classification and segmentation tasks, outperforming some CNN-based and Transformer-based methods.

References

[1]
Iro Armeni, Ozan Sener, Amir R. Zamir, Helen Jiang, Ioannis Brilakis, Martin Fischer, and Silvio Savarese. 2016. 3D Semantic Parsing of Large-Scale Indoor Spaces. 1534–1543. Retrieved March 29, 2023 from https://openaccess.thecvf.com/content_cvpr_2016/html/Armeni_3D_Semantic_Parsing_CVPR_2016_paper.html
[2]
Matan Atzmon, Haggai Maron, and Yaron Lipman. 2018. Point Convolutional Neural Networks by Extension Operators.
[3]
Marcos Barranquero, Alvaro Olmedo, Josefa Gómez, Abdelhamid Tayebi, Carlos Javier Hellín, and Francisco Saez de Adana. 2023. Automatic 3D Building Reconstruction from OpenStreetMap and LiDAR Using Convolutional Neural Networks. Sensors 23, 5 (January 2023), 2444.
[4]
Siheng Chen, Baoan Liu, Chen Feng, Carlos Vallespi-Gonzalez, and Carl Wellington. 2021. 3D Point Cloud Processing and Learning for Autonomous Driving: Impacting Map Creation, Localization, and Perception. IEEE Signal Processing Magazine 38, 1 (January 2021), 68–86.
[5]
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.
[6]
Meng-Hao Guo, Jun-Xiong Cai, Zheng-Ning Liu, Tai-Jiang Mu, Ralph R. Martin, and Shi-Min Hu. 2021. PCT: Point cloud transformer. Comp. Visual Media 7, 2 (June 2021), 187–199.
[7]
Mor Joseph-Rivlin, Alon Zvirin, and Ron Kimmel. 2019. Momen(e)t: Flavor the Moments in Learning to Classify Shapes. 0–0. Retrieved March 29, 2023 from https://openaccess.thecvf.com/content_ICCVW_2019/html/GMDL/Joseph-Rivlin_Momenet_Flavor_the_Moments_in_Learning_to_Classify_Shapes_ICCVW_2019_paper.html
[8]
Chaitanya Kaul, Joshua Mitton, Hang Dai, and Roderick Murray-Smith. 2021. CpT: Convolutional Point Transformer for 3D Point Cloud Processing. Retrieved June 17, 2023 from http://arxiv.org/abs/2111.10866
[9]
Roman Klokov and Victor Lempitsky. 2017. Escape From Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models. 863–872. Retrieved July 17, 2023 from https://openaccess.thecvf.com/content_iccv_2017/html/Klokov_Escape_From_Cells_ICCV_2017_paper.html
[10]
Truc Le and Ye Duan. 2018. PointGrid: A Deep Network for 3D Shape Understanding. 9204–9214. Retrieved July 17, 2023 from https://openaccess.thecvf.com/content_cvpr_2018/html/Le_PointGrid_A_Deep_CVPR_2018_paper.html
[11]
Jiaxin Li, Ben M. Chen, and Gim Hee Lee. 2018. SO-Net: Self-Organizing Network for Point Cloud Analysis. 9397–9406. Retrieved March 29, 2023 from https://openaccess.thecvf.com/content_cvpr_2018/html/Li_SO-Net_Self-Organizing_Network_CVPR_2018_paper.html
[12]
Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, and Baoquan Chen. 2018. PointCNN: Convolution On X-Transformed Points. Advances in Neural Information Processing Systems 31, (2018). Retrieved March 29, 2023 from https://proceedings.neurips.cc/paper_files/paper/2018/hash/f5f8590cd58a54e94377e6ae2eded4d9-Abstract.html
[13]
Yangyan Li, Soeren Pirk, Hao Su, Charles R Qi, and Leonidas J Guibas. 2016. FPNN: Field Probing Neural Networks for 3D Data. In Advances in Neural Information Processing Systems, Curran Associates, Inc. Retrieved July 17, 2023 from https://proceedings.neurips.cc/paper_files/paper/2016/hash/854d6fae5ee42911677c739ee1734486-Abstract.html
[14]
Zhi-Hao Lin, Sheng-Yu Huang, and Yu-Chiang Frank Wang. 2020. Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis. 1800–1809. Retrieved July 18, 2023 from https://openaccess.thecvf.com/content_CVPR_2020/html/Lin_Convolution_in_the_Cloud_Learning_Deformable_Kernels_in_3D_Graph_CVPR_2020_paper.html
[15]
Yahui Liu, Bin Tian, Yisheng Lv, Lingxi Li, and Fei-Yue Wang. 2023. Point cloud classification using content-based transformer via clustering in feature space. IEEE/CAA Journal of Automatica Sinica (2023), 1–9.
[16]
Daniel Maturana and Sebastian Scherer. 2015. VoxNet: A 3D Convolutional Neural Network for real-time object recognition. In 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 922–928.
[17]
Dejing Ni, AYC Nee, SK Ong, Huijun Li, Chengcheng Zhu, and Aiguo Song. 2018. Point cloud augmented virtual reality environment with haptic constraints for teleoperation. Transactions of the Institute of Measurement and Control 40, 15 (November 2018), 4091–4104.
[18]
S. M. Moein Peyghambarzadeh, Fatemeh Azizmalayeri, Hassan Khotanlou, and Amir Salarpour. 2020. Point-PlaneNet: Plane kernel based convolutional neural network for point clouds analysis. Digital Signal Processing 98, (March 2020), 102633.
[19]
Anh Viet Phan, Minh Le Nguyen, Yen Lam Hoang Nguyen, and Lam Thu Bui. 2018. DGCNN: A convolutional neural network over large-scale labeled graphs. Neural Networks 108, (December 2018), 533–543.
[20]
François Pomerleau, Francis Colas, and Roland Siegwart. 2015. A Review of Point Cloud Registration Algorithms for Mobile Robotics. ROB 4, 1 (May 2015), 1–104.
[21]
Charles R. Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. 2017. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. 652–660. Retrieved March 29, 2023 from https://openaccess.thecvf.com/content_cvpr_2017/html/Qi_PointNet_Deep_Learning_CVPR_2017_paper.html
[22]
Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. 2017. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In Advances in Neural Information Processing Systems, Curran Associates, Inc. Retrieved March 29, 2023 from https://proceedings.neurips.cc/paper/2017/hash/d8bf84be3800d12f74d8b05e9b89836f-Abstract.html
[23]
Guocheng Qian, Yuchen Li, Houwen Peng, Jinjie Mai, Hasan Hammoud, Mohamed Elhoseiny, and Bernard Ghanem. 2022. PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies. Advances in Neural Information Processing Systems 35, (December 2022), 23192–23204.
[24]
Yongming Rao, Jiwen Lu, and Jie Zhou. 2019. Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition. 452–460. Retrieved July 18, 2023 from https://openaccess.thecvf.com/content_CVPR_2019/html/Rao_Spherical_Fractal_Convolutional_Neural_Networks_for_Point_Cloud_Recognition_CVPR_2019_paper.html
[25]
Gernot Riegler, Ali Osman Ulusoy, and Andreas Geiger. 2017. OctNet: Learning Deep 3D Representations at High Resolutions. 3577–3586. Retrieved June 17, 2023 from https://openaccess.thecvf.com/content_cvpr_2017/html/Riegler_OctNet_Learning_Deep_CVPR_2017_paper.html
[26]
Shuran Song, Samuel P. Lichtenberg, and Jianxiong Xiao. 2015. SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite. 567–576. Retrieved March 29, 2023 from https://openaccess.thecvf.com/content_cvpr_2015/html/Song_SUN_RGB-D_A_2015_CVPR_paper.html
[27]
Hang Su, Subhransu Maji, Evangelos Kalogerakis, and Erik Learned-Miller. 2015. Multi-View Convolutional Neural Networks for 3D Shape Recognition. 945–953. Retrieved June 17, 2023 from https://www.cv-foundation.org/openaccess/content_iccv_2015/html/Su_Multi-View_Convolutional_Neural_ICCV_2015_paper.html
[28]
Yehui Tang, Kai Han, Jianyuan Guo, Chang Xu, Yanxi Li, Chao Xu, and Yunhe Wang. An Image Patch is a Wave: Quantum Inspired Vision MLP.
[29]
Mikaela Angelina Uy, Quang-Hieu Pham, Binh-Son Hua, Thanh Nguyen, and Sai-Kit Yeung. 2019. Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data. 1588–1597. Retrieved March 29, 2023 from https://openaccess.thecvf.com/content_ICCV_2019/html/Uy_Revisiting_Point_Cloud_Classification_A_New_Benchmark_Dataset_and_Classification_ICCV_2019_paper.html
[30]
Chu Wang, Babak Samari, and Kaleem Siddiqi. 2018. Local Spectral Graph Convolution for Point Set Feature Learning. 52–66. Retrieved July 18, 2023 from https://openaccess.thecvf.com/content_ECCV_2018/html/Chu_Wang_Local_Spectral_Graph_ECCV_2018_paper.html
[31]
Sungmin Woo, Dogyoon Lee, Junhyeop Lee, Sangwon Hwang, Woojin Kim, and Sangyoun Lee. 2021. CKConv: Learning Feature Voxelization for Point Cloud Analysis.
[32]
Wenxuan Wu, Zhongang Qi, and Li Fuxin. 2019. PointConv: Deep Convolutional Networks on 3D Point Clouds. 9621–9630. Retrieved March 29, 2023 from https://openaccess.thecvf.com/content_CVPR_2019/html/Wu_PointConv_Deep_Convolutional_Networks_on_3D_Point_Clouds_CVPR_2019_paper.html
[33]
Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3D ShapeNets: A Deep Representation for Volumetric Shapes. 1912–1920. Retrieved March 29, 2023 from https://www.cv-foundation.org/openaccess/content_cvpr_2015/html/Wu_3D_ShapeNets_A_2015_CVPR_paper.html
[34]
Mutian Xu, Runyu Ding, Hengshuang Zhao, and Xiaojuan Qi. 2021. PAConv: Position Adaptive Convolution With Dynamic Kernel Assembling on Point Clouds. 3173–3182. Retrieved June 17, 2023 from https://openaccess.thecvf.com/content/CVPR2021/html/Xu_PAConv_Position_Adaptive_Convolution_With_Dynamic_Kernel_Assembling_on_Point_CVPR_2021_paper.html
[35]
Yifan Xu, Tianqi Fan, Mingye Xu, Long Zeng, and Yu Qiao. 2018. SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters. 87–102. Retrieved April 17, 2023 from https://openaccess.thecvf.com/content_ECCV_2018/html/Yifan_Xu_SpiderCNN_Deep_Learning_ECCV_2018_paper.html
[36]
Li Yi, Vladimir G. Kim, Duygu Ceylan, I-Chao Shen, Mengyan Yan, Hao Su, Cewu Lu, Qixing Huang, Alla Sheffer, and Leonidas Guibas. 2016. A scalable active framework for region annotation in 3D shape collections. ACM Trans. Graph. 35, 6 (December 2016), 210:1-210:12.
[37]
Xumin Yu, Lulu Tang, Yongming Rao, Tiejun Huang, Jie Zhou, and Jiwen Lu. 2022. Point-BERT: Pre-Training 3D Point Cloud Transformers With Masked Point Modeling. 19313–19322. Retrieved March 29, 2023 from https://openaccess.thecvf.com/content/CVPR2022/html/Yu_Point-BERT_Pre-Training_3D_Point_Cloud_Transformers_With_Masked_Point_Modeling_CVPR_2022_paper.html
[38]
Wentao Yuan, David Held, Christoph Mertz, and Martial Hebert. 2019. Iterative Transformer Network for 3D Point Cloud.
[39]
Hengshuang Zhao, Li Jiang, Chi-Wing Fu, and Jiaya Jia. 2019. PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing. 5565–5573. Retrieved March 29, 2023 from https://openaccess.thecvf.com/content_CVPR_2019/html/Zhao_PointWeb_Enhancing_Local_Neighborhood_Features_for_Point_Cloud_Processing_CVPR_2019_paper.html
[40]
Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip H. S. Torr, and Vladlen Koltun. 2021. Point Transformer. 16259–16268. Retrieved March 29, 2023 from https://openaccess.thecvf.com/content/ICCV2021/html/Zhao_Point_Transformer_ICCV_2021_paper.html?ref=; https://githubhelp.com
[41]
Shen Zheng, Jinqian Pan, Changjie Lu, and Gaurav Gupta. 2022. PointNorm: Dual Normalization is All You Need for Point Cloud Analysis.
[42]
Haoran Zhou, Yidan Feng, Mingsheng Fang, Mingqiang Wei, Jing Qin, and Tong Lu. 2021. Adaptive Graph Convolution for Point Cloud Analysis. 4965–4974. Retrieved March 29, 2023 from https://openaccess.thecvf.com/content/ICCV2021/html/Zhou_Adaptive_Graph_Convolution_for_Point_Cloud_Analysis_ICCV_2021_paper.html

Index Terms

  1. PointWave-MLP: Point Cloud Analysis Based on Wave-MLP Architecture
          Index terms have been assigned to the content through auto-classification.

          Recommendations

          Comments

          Information & Contributors

          Information

          Published In

          cover image ACM Other conferences
          CCRIS '23: Proceedings of the 2023 4th International Conference on Control, Robotics and Intelligent System
          August 2023
          215 pages
          ISBN:9798400708190
          DOI:10.1145/3622896
          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 the author(s) 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: 03 October 2023

          Permissions

          Request permissions for this article.

          Check for updates

          Author Tags

          1. Deep learning
          2. MLP-like architecture
          3. Phase-awaring token mixing
          4. Point cloud analysis

          Qualifiers

          • Research-article
          • Research
          • Refereed limited

          Funding Sources

          • Medium and Long-term Development Plan Project of National Radio and Tevevision Administration of China

          Conference

          CCRIS 2023

          Contributors

          Other Metrics

          Bibliometrics & Citations

          Bibliometrics

          Article Metrics

          • 0
            Total Citations
          • 33
            Total Downloads
          • Downloads (Last 12 months)18
          • Downloads (Last 6 weeks)3
          Reflects downloads up to 20 Jan 2025

          Other Metrics

          Citations

          View Options

          Login options

          View options

          PDF

          View or Download as a PDF file.

          PDF

          eReader

          View online with eReader.

          eReader

          HTML Format

          View this article in HTML Format.

          HTML Format

          Media

          Figures

          Other

          Tables

          Share

          Share

          Share this Publication link

          Share on social media