Researching

Journals
  • Advanced Photonics
  • Photonics Insights
  • Advanced Photonics Nexus
  • Photonics Research
  • Advanced Imaging
  • View All Journals
  • Chinese Optics Letters
  • High Power Laser Science and Engineering
    • Articles
  • Optics
  • Physics
  • Geography
  • View All Subjects
    • Conferences
  • CIOP
  • HPLSE
  • AP
  • View All Events
    • News
    About CLP
    Search by keywords or author
    Journals >Laser & Optoelectronics Progress >Volume 60 >Issue 2 >Page 0210012 > Article
    • Laser & Optoelectronics Progress
    • Vol. 60, Issue 2, 0210012 (2023)
    Point Cloud Completion Network Based on Multiencoders and Residual-Transformer
    Hui Gao, Zhijing Yang*, Wing-Kuen Ling, Jiangzhong Cao, and Weijie Li
    Author Affiliations
  • School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, Guangdong, China
    • show less
    DOI: 10.3788/LOP213314 Cite this Article Set citation alerts
    Hui Gao, Zhijing Yang, Wing-Kuen Ling, Jiangzhong Cao, Weijie Li. Point Cloud Completion Network Based on Multiencoders and Residual-Transformer[J]. Laser & Optoelectronics Progress, 2023, 60(2): 0210012 Copy Citation Text show less
    Point cloud completion network based on multi-encoders and Residual-Transformer
    Fig. 1. Point cloud completion network based on multi-encoders and Residual-Transformer
    Download full size
    Structure of PRN
    Fig. 2. Structure of PRN
    Download full size
    Entire completion process of the proposed model. (a) Original point cloud; (b) predicted missing part; (c) complete point cloud after merging Fig.3 (a) and Fig.3 (b); (d) point cloud after sampling; (e) complete point cloud after enhancement; (f) ground truth
    Fig. 3. Entire completion process of the proposed model. (a) Original point cloud; (b) predicted missing part; (c) complete point cloud after merging Fig.3 (a) and Fig.3 (b); (d) point cloud after sampling; (e) complete point cloud after enhancement; (f) ground truth
    Download full size
    Comparison of completion visualization effects of different methods on Shapenet-Part dataset
    Fig. 4. Comparison of completion visualization effects of different methods on Shapenet-Part dataset
    Download full size
    Comparison of completion visualization effects of ablation study on Shapenet-Part dataset
    Fig. 5. Comparison of completion visualization effects of ablation study on Shapenet-Part dataset
    Download full size
    CategoryMSN［14］PF-Net［1］FCAE［26］RP-MLP［26］Proposed method
    Average8.395/5.70411.131/4.28920.121/15.9327.514/3.3965.035/3.294
    Airplane3.113/3.5004.604/2.9976.980/7.0472.892/2.2122.164/2.641
    Bag15.393/7.94221.350/7.18434.774/29.04514.232/5.7487.127/3.340
    Cap16.824/5.84228.984/3.71952.914/37.09417.016/2.5276.950/3.065
    Car8.443/6.9919.643/3.20619.982/15.5508.683/2.5166.103/2.592
    Chair5.934/4.4347.803/2.77416.408/13.7336.049/2.0514.107/2.050
    Guitar5.226/3.3653.195/3.0683.276/3.1851.822/2.3811.693/2.168
    Lamp19.873/9.81924.143/10.55939.082/21.31915.675/9.38914.506/10.085
    Laptop3.543/3.9104.879/2.2629.252/9.6232.832/1.4302.110/1.195
    Motorbike6.802/7.1786.473/5.02814.094/11.5926.197/4.1625.188/3.701
    Mug8.199/6.34010.538/3.77425.223/22.1197.464/3.0545.481/3.316
    Pistol5.092/6.3497.613/4.94410.898/10.1155.399/3.9523.350/4.051
    Skateboard3.441/3.7665.562/2.7888.981/8.9962.693/1.9941.812/2.101
    Table7.257/4.7099.919/3.45419.712/17.6996.722/2.7374.865/2.513
    Table 1. Pred→GT/Pred←GT of different methods, results are magnified by 10000
    MethodAirplaneBagCapCarChairGuitarLamp
    Proposed method

    2.164/

    2.461

    7.127/

    3.340

    6.950/

    3.065

    6.103/

    2.592

    4.107/

    2.050

    1.693/

    2.168

    14.506/

    10.085

    Proposed method without RT

    3.208/

    3.356

    9.793/

    6.232

    11.605/

    4.262

    8.464/

    3.730

    6.407/

    3.413

    1.853/

    3.214

    18.528/

    12.221

    MethodLaptopMotorbikeMugPistolSkateboardTableAverage
    Proposed method

    2.110/

    1.195

    5.188/

    3.701

    5.481/

    3.316

    3.350/

    4.051

    1.812/

    2.101

    4.865/

    2.513

    5.035/

    3.294

    Proposed method without RT

    2.975/

    2.013

    5.748/

    5.525

    7.922/

    4.639

    5.621/

    6.031

    7.391/

    4.809

    6.560/

    4.103

    7.390/

    4.888

    Table 2. Pred→GT/Pred←GT comparison of ablation study, results are magnified by 10000
    MethodAirplaneBagCapCarChairGuitarLamp
    Proposed method

    2.164/

    2.461

    7.127/

    3.340

    6.950/

    3.065

    6.103/

    2.592

    4.107/

    2.050

    1.693/

    2.168

    14.506/

    10.085

    Proposed method w/o Lo

    5.055/

    7.812

    18.436/

    4.450

    9.441/

    2.961

    7.561/

    3.938

    12.959/

    4.838

    4.534/

    3.363

    15.442/

    14.081

    MethodLaptopMotorbikeMugPistolSkateboardTableAverage
    Proposed method

    2.110/

    1.195

    5.188/

    3.701

    5.481/

    3.316

    3.350/

    4.051

    1.812/

    2.101

    4.865/

    2.513

    5.035/

    3.294

    Proposed method w/o Lo

    3.198/

    4.156

    3.229/

    6.181

    10.524/

    4.145

    4.440/

    10.144

    5.669/

    6.232

    7.862/

    4.432

    8.335/

    5.903

    Table 3. Pred→GT/Pred←GT comparison of ablation study, results are magnified by 10000
    Abstract
    Get PDF(in Chinese)
    Figures&Tables (8)
    Equations (11)
    References (26)
    Cited By (1)
    Get Citation
    Copy Citation Text
    Hui Gao, Zhijing Yang, Wing-Kuen Ling, Jiangzhong Cao, Weijie Li. Point Cloud Completion Network Based on Multiencoders and Residual-Transformer[J]. Laser & Optoelectronics Progress, 2023, 60(2): 0210012
    Download Citation
    Set citation alerts for the article
    Tools
    Share
    Set citation alerts for the article
    Save the article for my favorites
    Paper Information
    Recommended Topics
    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology