基于对称性先验的船舶点云补全方法

doi:10.3969/j.issn.0255-8297.2026.01.011

摘要/Abstract

摘要： 受制于单视角扫描的固有局限性和船体复杂结构的空间遮挡效应，现有采集系统普遍面临背侧点云大范围缺损的技术瓶颈。针对这一挑战，本文提出了一种基于对称性先验的船舶点云补全方法。该方法无需标注数据，利用船舶对称结构特性作为先验驱动，实现船舶背侧点云的有效补全。首先，基于船舶几何拓扑分析建立多类型船舶的船体纵剖面特征提取模型；其次，提出对称变换场生成算法，将缺损点云沿船体纵剖面进行镜像补全，构建候选补全点云集合；再次，设计候选点云与原始点云间的平均最近邻质量评估函数，实现最优补全结果的鲁棒性筛选。实验结果表明，该方法在无任何训练样本条件下，能够对尖头船、平头船等典型船型的背侧点云进行有效补全，且满足实时采集场景的需求。

关键词: 对称驱动补全, 点云降噪, 无监督算法, 特征提取

Abstract: Due to the inherent limitations of single-view scanning and the spatial occlusion effects of complex ship hull structures, existing data collection systems commonly face the technical bottleneck of extensive missing data in back-side point clouds. To address this challenge, this paper proposed a ship point cloud completion method based on symmetry priors. This method operated without the need for labeling data and utilized the symmetrical structural characteristics of ships as prior-driven knowledge to effectively complete the back-side point clouds. First, a feature extraction model of the longitudinal centerplane for various types of ship hull was established based on geometric topology analysis of the ships. Then, a symmetry transformation field generation algorithm was proposed to make a mirror completion for the missing point clouds along the longitudinal centerplane of the ship hull, thereby constructing a candidate point cloud set for completion. Finally, an average nearest neighbor quality assessment function between the candidate point clouds and the original point clouds was designed to robustly select the optimal completion result. Experimental results show that the proposed method effectively completes the back-side point clouds of typical ship types, such as sharp-prowed and flat-bottomed ships, without requiring any training samples, and it meets the requirements of real-time data collection scenarios.

Key words: symmetry-driven completion, point cloud denoising, unsupervised algorithm, feature extraction

中图分类号:

TP958.98

曾银川, 郑博, 王宪保, 项圣. 基于对称性先验的船舶点云补全方法[J]. 应用科学学报, 2026, 44(1): 166-180.

ZENG Yinchuan, ZHENG Bo, WANG Xianbao, XIANG Sheng. Completion Method for Ship Point Cloud Based on Symmetry Priors[J]. Journal of Applied Sciences, 2026, 44(1): 166-180.

参考文献

[1] 陈建文, 赵丽丽, 任蓝草, 等. 深度学习点云质量增强方法综述[J]. 中国图象图形学报, 2023, 28(11): 3295-3319. Chen J W, Zhao L L, Ren L C, et al. Survey of point cloud quality enhancement methods based on deep learning [J]. Journal of Image and Graphics, 2023, 28(11): 3295-3319. (in Chinese)
[2] 马骥, 石岩. 现代化背景下的内河航道高质量发展路径研究[J]. 中国水运, 2024(23): 17-20. Ma J, Shi Y. Research on high-quality development path of inland waterway under modernization background [J]. China Water Transport, 2024(23): 17-20. (in Chinese)
[3] 汪骥, 柳丛, 李瑞, 等. 基于点云目标检测算法的船体分段合拢面构件识别方法[J]. 船舶工程, 2024, 46(7): 19-25, 89. Wang J, Liu C, Li R, et al. Component recognition method of hull block closing surface based on point cloud object detection algorithm [J]. Ship Engineering, 2024, 46(7): 19-25, 89. (in Chinese)
[4] 胡伏原, 李晨露, 周涛, 等. 面向深度学习的三维点云补全算法综述[J]. 中国图象图形学报, 2025, 30(2): 309-333. Hu F Y, Li C L, Zhou T, et al. Survey of 3D point cloud completion algorithms based on deep learning [J]. Journal of Image and Graphics, 2025, 30(2): 309-333. (in Chinese)
[5] 李维刚, 曹文杰, 李金灵. 基于自适应邻域特征融合的多阶段点云补全网络[J]. 计算机应用, 2025, 45(10): 3294-3301. Li W G, Cao W J, Li J L. Multi-stage point cloud completion network based on adaptive neighborhood feature fusion [J]. Journal of Computer Applications, 2025, 45(10): 3294-3301. (in Chinese)
[6] Dai A, Qi C R, Nießner M. Shape completion using 3D-encoder-predictor CNNs and shape synthesis [C]// IEEE Conference on Computer Vision and Pattern Recognition, 2017: 5868-5877.
[7] Xie H, Yao H, Zhou S, et al. GRNet: gridding residual network for dense point cloud completion [C]//European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 365-381.
[8] 周静, 胡怡宇, 胡成玉, 等. 基于点云补全和多分辨Transformer的弱感知目标检测方法[J]. 计算机应用, 2023, 43(7): 2155-2165. Zhou J, Hu Y Y, Hu C Y, et al. Weak perception object detection method based on point cloud completion and multi-resolution Transformer [J]. Journal of Computer Applications, 2023, 43(7): 2155-2165. (in Chinese)
[9] Su H, Maji S, Kalogerakis E, et al. Multi-view convolutional neural networks for 3D shape recognition [C]// IEEE International Conference on Computer Vision, 2015: 945-953.
[10] Hu T, Han Z, Zwicker M. 3D shape completion with multi-view consistent inference [C]// AAAI Conference on Artificial Intelligence, 2020, 34(7): 10997-11004.
[11] Yuan W, Khot T, Held D, et al. PCN: point completion network [C]// International Conference on 3D Vision (3DV). IEEE, 2018: 728-737.
[12] Tchapmi L P, Kosaraju V, Rezatofighi H, et al. TopNet: structural point cloud decoder [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 383-392.
[13] Tesema K W, Hill L, Jones M W, et al. Point cloud completion: a survey [J]. IEEE Transactions on Visualization and Computer Graphics, 2023, 30(10): 6880-6899.
[14] Zhang X, Feng Y, Li S, et al. View-guided point cloud completion [C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 15890-15899.
[15] Caruso C, Quarta F. Interpolation methods comparison [J]. Computers & Mathematics with Applications, 1998, 35(12): 109-126.
[16] Cai Z, Wang C, Wen C, et al. 3D-PatchMatch: an optimization algorithm for point cloud completion [C]// 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM). IEEE, 2015: 157-161.
[17] Pauly M, Mitra N J, Giesen J, et al. Example-based 3D scan completion [C]//Symposium on Geometry Processing, 2005: 23-32.
[18] Kazhdan M, Funkhouser T, Rusinkiewicz S. Symmetry descriptors and 3D shape matching [C]// Eurographics/ACM SIGGRAPH Symposium on Geometry processing, 2004: 115-123.
[19] Kroemer O, Amor H B, Ewerton M, et al. Point cloud completion using extrusions [C]// 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012). IEEE, 2012: 680-685.
[20] Rumezhak T, Dobosevych O, Hryniv R, et al. Towards realistic symmetry-based completion of previously unseen point clouds [C]//IEEE/CVF International Conference on Computer Vision, 2021: 2542-2550.
[21] 吴姝, 王涛, 崔英花, 等. 一种参数自适应的统计滤波降噪算法[J]. 应用激光, 2024, 44(9): 124-132. Wu S, Wang T, Cui Y H, et al. A parameter-adaptive statistical filtering denoising algorithm [J]. Applied Laser, 2024, 44(9): 124-132. (in Chinese)
[22] Grigoropoulos G J. Hydrodynamic design of ships [J]. Journal of Marine Science and Engineering, 2022, 10(4): 512.