计算机工程与应用2025，Vol.61Issue(10)：192-202,11.DOI:10.3778/j.issn.1002-8331.2407-0232
基于边缘区域特征细化的无监督点云补全网络研究
Research on Unsupervised Point Cloud Completion Network Based on Edge Regional Feature Refinement
摘要
Abstract
Existing point cloud completion methods focus on area features for geometric structure capture,but often over-look critical edge details,which describe the details at the corners or complex boundaries of the point cloud,and are the key to recover the refined point cloud.In order to achieve the complementary advantages of region features and edge details,an unsupervised point cloud completion network based on edge regional feature refinement is proposed.A region-edge feature extractor is designed,which captures the region features of the point cloud via DGCNN(dynamic graph convolutional neural network),and then filters the edge features by constructing a normalized map of the spatial location of the point cloud.A missing-point generator is proposed to incorporate the extracted edge features into the local region to generate a relatively complete rough point cloud.An unsupervised point refiner is constructed to predict key points describing the structure,and further refines the rough point cloud into a complete point cloud with rich details.Extensive experiments on PCN,ShapeNet-55/34,MVP and KITTI datasets demonstrate significant performance gains.In particular,the MMD index is improved by 3.7%and 2.2%compared to the SeedFormer and ProxyFormer.关键词
点云补全/边缘特征/特征互补/无监督细化器Key words
point cloud completion/edge features/feature complementarity/unsupervised point refiner分类
信息技术与安全科学引用本文复制引用
陈汉秋,张惊雷,贾鑫..基于边缘区域特征细化的无监督点云补全网络研究[J].计算机工程与应用,2025,61(10):192-202,11.基金项目
国家自然科学基金青年项目(62302335). （62302335）
