Point-PC: Point cloud completion guided by prior knowledge via causal inference

IF 7.3 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Xuesong Gao, Chuanqi Jiao, Ruidong Chen, Weijie Wang, Weizhi Nie
{"title":"Point-PC: Point cloud completion guided by prior knowledge via causal inference","authors":"Xuesong Gao,&nbsp;Chuanqi Jiao,&nbsp;Ruidong Chen,&nbsp;Weijie Wang,&nbsp;Weizhi Nie","doi":"10.1049/cit2.12379","DOIUrl":null,"url":null,"abstract":"<p>The goal of point cloud completion is to reconstruct raw scanned point clouds acquired from incomplete observations due to occlusion and restricted viewpoints. Numerous methods use a partial-to-complete framework, directly predicting missing components via global characteristics extracted from incomplete inputs. However, this makes detail recovery challenging, as global characteristics fail to provide complete missing component specifics. A new point cloud completion method named Point-PC is proposed. A memory network and a causal inference model are separately designed to introduce shape priors and select absent shape information as supplementary geometric factors for aiding completion. Concretely, a memory mechanism is proposed to store complete shape features and their associated shapes in a key-value format. The authors design a pre-training strategy that uses contrastive learning to map incomplete shape features into the complete shape feature domain, enabling retrieval of analogous shapes from incomplete inputs. In addition, the authors employ backdoor adjustment to eliminate confounders, which are shape prior components sharing identical semantic structures with incomplete inputs. Experiments conducted on three datasets show that our method achieves superior performance compared to state-of-the-art approaches. The code for Point-PC can be accessed by https://github.com/bizbard/Point-PC.git.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"10 4","pages":"1007-1018"},"PeriodicalIF":7.3000,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12379","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"CAAI Transactions on Intelligence Technology","FirstCategoryId":"94","ListUrlMain":"https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/cit2.12379","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

The goal of point cloud completion is to reconstruct raw scanned point clouds acquired from incomplete observations due to occlusion and restricted viewpoints. Numerous methods use a partial-to-complete framework, directly predicting missing components via global characteristics extracted from incomplete inputs. However, this makes detail recovery challenging, as global characteristics fail to provide complete missing component specifics. A new point cloud completion method named Point-PC is proposed. A memory network and a causal inference model are separately designed to introduce shape priors and select absent shape information as supplementary geometric factors for aiding completion. Concretely, a memory mechanism is proposed to store complete shape features and their associated shapes in a key-value format. The authors design a pre-training strategy that uses contrastive learning to map incomplete shape features into the complete shape feature domain, enabling retrieval of analogous shapes from incomplete inputs. In addition, the authors employ backdoor adjustment to eliminate confounders, which are shape prior components sharing identical semantic structures with incomplete inputs. Experiments conducted on three datasets show that our method achieves superior performance compared to state-of-the-art approaches. The code for Point-PC can be accessed by https://github.com/bizbard/Point-PC.git.

Abstract Image

Abstract Image

Abstract Image

Point- pc:通过因果推理,在先验知识指导下完成点云
点云补全的目标是重建由于遮挡和视点受限而产生的不完整观测的原始扫描点云。许多方法使用部分到完整的框架,通过从不完整输入中提取的全局特征直接预测缺失的组件。然而,这使得详细的恢复具有挑战性,因为全局特征无法提供完整的缺失组件细节。提出了一种新的点云补全方法——point - pc。分别设计了记忆网络和因果推理模型,引入形状先验,选择缺失的形状信息作为辅助补全的补充几何因子。具体而言,提出了一种以键值格式存储完整形状特征及其关联形状的存储机制。作者设计了一种预训练策略,该策略使用对比学习将不完整形状特征映射到完整形状特征域,从而能够从不完整输入中检索类似形状。此外,作者采用后门调整来消除混杂因素,这些混杂因素是具有不完整输入的形状先验成分,它们具有相同的语义结构。在三个数据集上进行的实验表明,与最先进的方法相比,我们的方法具有优越的性能。Point-PC的代码可以通过https://github.com/bizbard/Point-PC.git访问。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CAAI Transactions on Intelligence Technology
CAAI Transactions on Intelligence Technology COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-
CiteScore
11.00
自引率
3.90%
发文量
134
审稿时长
35 weeks
期刊介绍: CAAI Transactions on Intelligence Technology is a leading venue for original research on the theoretical and experimental aspects of artificial intelligence technology. We are a fully open access journal co-published by the Institution of Engineering and Technology (IET) and the Chinese Association for Artificial Intelligence (CAAI) providing research which is openly accessible to read and share worldwide.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信