基于注意力的多阶段点云补全网络
Attention-Based Multi-Stage Network for Point Cloud Completion
尹溪洋 1周佩 2朱江平2
作者信息
- 1. 四川大学计算机学院,四川 成都 610065
- 2. 四川大学计算机学院,四川 成都 610065;四川大学视觉合成图形图像技术重点学科实验室,四川 成都 610065
- 折叠
摘要
点云补全指利用不完整点云数据重建完整三维模型的过程.现有的大多数点云补全方法受点云无序性和不规则性影响,难以有效地重建局部细节信息,进而影响补全精度.为解决这个问题,提出基于注意力的多阶段点云补全网络.设计了满足置换不变性的金字塔式点云特征提取器以建立局部内点间的依赖以及不同局部间的相关性,在提取全局特征信息的同时加强对局部特征信息的提取.在点云重建过程中,采用由粗到精的方式,首先生成一个低分辨率的种子点云,然后逐步丰富种子点云的局部细节,得到更加精细且稠密的点云.在公开数据集PCN下进行的对比实验结果证明了所提网络能够有效重建局部细节信息,与现有方法相比,在补全精度上提升了至少5.98%.消融实验结果也进一步验证了所提注意力模块的有效性.
Abstract
Point cloud completion refers to the process for reconstructing a complete 3D model using incomplete point cloud data.Most of the existing point cloud completion methods are limited by the point cloud disorder and irregularity,which makes it difficult to reconstruct the local detail information,thus affecting the completion accuracy.To solve this problem,an attention-based multi-stage network for point cloud completion is proposed.A pyramid feature extractor that satisfies the replacement invariance is designed to establish the dependence between points within a localization as well as the correlation between different localizations,so as to enhance the extraction of local information while extracting global feature information.In the point cloud reconstruction process,a coarse-to-fine completion method is adopted to first generate a low-resolution seed point cloud,and then gradually enrich the local details of the seed point cloud to obtain a finer and denser point cloud.Comparison results of the experiments conducted on the public dataset PCN demonstrate that the proposed network can effectively reconstruct the local detail information,and improves the completion accuracy by at least 5.98%over the existing methods.The ablation experimental results also further validate the effectiveness of the designed attention module.
关键词
点云/点云补全/自注意力/交叉注意力/几何细节感知Key words
point cloud/point cloud completion/self-attention/cross-attention/geometric details perception引用本文复制引用
基金项目
国家自然科学基金(62101364)
国家自然科学基金(61901287)
四川省中央引导地方科技发展计划(22ZYD0111)
中国博士后科学基金(2021M692260)
四川省科技重大专项(2021YFG0195)
四川省科技重大专项(2022YFG0053)
出版年
2024
NETL
NSTL
万方数据