Researching | Attention-Enhanced Multiscale Dual-Feature Point Cloud Completion Method

Laser & Optoelectronics Progress, Volume. 62, Issue 16, 1637004(2025)

Attention-Enhanced Multiscale Dual-Feature Point Cloud Completion Method

Tianli Wang¹, Zequn Zhang^1、*, Jie Chen¹, Dunbing Tang¹, Lanlan Jiang², and Lingfei Qian³

Author Affiliations

¹College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, Jiangsu , China

²Nanjing Nanrui Information Communication Technology, Nanjing 210003, Jiangsu , China

³College of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, Jiangsu , China

show less

Abstract Get PDF(in Chinese)

Figures&Tables (13)

References (23)

Paper Information

References(23)

[1] Sun J K, Yang Z H, Li F F et al. Projected feature assisted coarse to fine point cloud registration method for large-size 3D measurement[J]. Optics Express, 31, 18379-18398(2023).

[2] Tang F Z, Zhang S T, Zhu B C et al. Outdoor large-scene 3D point cloud reconstruction based on transformer[J]. Frontiers in Physics, 12, 1474797(2024).

[3] Shu J, Wu Q, Tan L et al. CWGA-Net: center-weighted graph attention network for 3D object detection from point clouds[J]. Image and Vision Computing, 152, 105314(2024).

[4] Mei R S, Conway C H, Bimrose M V et al. Deep learning of 3D point clouds for detecting geometric defects in gears[J]. Manufacturing Letters, 41, 1324-1333(2024).

[5] Zhang B, Wang H S, You S L et al. A small-size 3d object detection network for analyzing the sparsity of raw lidar point cloud[J]. Journal of Russian Laser Research, 44, 646-655(2023).

[6] Chen B W, Shi S, Sun J et al. Hyperspectral lidar point cloud segmentation based on geometric and spectral information[J]. Optics Express, 27, 24043-24059(2019).

[7] Han L Y, Lin S L, Zhao M et al. 3D object detection based on spherical semantic multi-modal fusion[J/OL], 1-8. https://kns.cnki.net/kcms/detail/32.1347.TN.20241205.1003.002.html

[8] Mukkapati N, Nalluri A, Likki V K R et al. A 3D CNN model framework for early identification and classification of Alzheimer’s in brain MRI images[J]. Mathematical Modelling of Engineering Problems, 11, 2833-2839(2024).

[9] Zaboli M, Rastiveis H, Hosseiny B et al. D-Net: a density-based convolutional neural network for mobile LiDAR point clouds classification in urban areas[J]. Remote Sensing, 15, 2317(2023).

[10] Pauly M, Mitra N J, Giesen J et al. Example-based 3D scan completion[EB/OL]. https://graphics.stanford.edu/~niloy/research/shape_completion/shape_completion_sgp_05.html#

[11] Kim V G, Li W, Mitra N J et al. Learning part-based templates from large collections of 3D shapes[J]. ACM Transactions on Graphics, 32, 70(2013).

[12] Li Y Y, Dai A, Guibas L et al. Database-assisted object retrieval for real-time 3D reconstruction[J]. Computer Graphics Forum, 34, 435-446(2015).

[13] Liu C J, Li J, Zhang S F et al. A point clouds filtering algorithm based on grid partition and moving least squares[J]. Procedia Engineering, 28, 476-482(2012).

[14] Charles R Q, Hao S, Mo K C et al. PointNet: deep learning on point sets for 3D classification and segmentation[C], 77-85(2017).

[15] Yang Y Q, Feng C, Shen Y R et al. FoldingNet: point cloud auto-encoder via deep grid deformation[C], 206-215(2018).

[16] Yuan W T, Khot T, Held D et al. PCN: point completion network[C], 728-737(2018).

[17] Huang Z T, Yu Y K, Xu J W et al. PF-Net: point fractal network for 3D point cloud completion[C], 7659-7667(2020).

[18] Hu F, Chen H H, Lu X Q et al. SPCNet: stepwise point cloud completion network[J]. Computer Graphics Forum, 41, 153-164(2022).

[19] Wang Y, Sun Y B, Liu Z W et al. Dynamic graph CNN for learning on point clouds[J]. ACM Transactions on Graphics, 38, 146(2019).

[20] Guo M H, Cai J X, Liu Z N et al. PCT: point cloud transformer[J]. Computational Visual Media, 7, 187-199(2021).

[21] Tchapmi L P, Kosaraju V, Rezatofighi H et al. TopNet: structural point cloud decoder[C], 383-392(2019).

[22] Yu X M, Rao Y M, Wang Z Y et al. PoinTr: diverse point cloud completion with geometry-aware transformers[C], 12478-12487(2021).

[23] Chang A X, Funkhouser T, Guibas L et al. ShapeNet: an information-rich 3D model repository[EB/OL]. https://arxiv.org/abs/1512.03012v1

Tools

Get Citation

Copy Citation Text

Tianli Wang, Zequn Zhang, Jie Chen, Dunbing Tang, Lanlan Jiang, Lingfei Qian. Attention-Enhanced Multiscale Dual-Feature Point Cloud Completion Method[J]. Laser & Optoelectronics Progress, 2025, 62(16): 1637004

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Digital Image Processing

Received: Jan. 9, 2025

Accepted: Mar. 14, 2025

Published Online: Aug. 6, 2025

The Author Email: Zequn Zhang (zhjj370@nuaa.edu.cn)

DOI:10.3788/LOP250484

CSTR:32186.14.LOP250484

Topics

laser devices and laser physics

Lasers and Laser Optics

laser manufacturing

Instrumentation, Measurement and Metrology