Point Cloud Completion via Self-Projected View Augmentation and Implicit Field Constraint
文献类型：期刊论文
| 作者 | Xiao, Haihong5; He, Ying4; Liu, Hao4; Kang, Wenxiong2,3,5; Li YQ(李玉琼)1
|
| 刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
 |
| 出版日期 | 2024-11-01 |
| 卷号 | 34期号:11页码:11564-11578 |
| 关键词 | 3D point cloud point cloud completion 3D vision |
| ISSN号 | 1051-8215 |
| DOI | 10.1109/TCSVT.2024.3424776 |
| 通讯作者 | Kang, Wenxiong(auwxkang@scut.edu.cn) |
| 英文摘要 | Recent advances in point cloud completion make it possible to simultaneously recover complete shapes and fine details from partial point clouds captured by professional 3D devices, such as Lidar, or consumer cameras, such as iPhones. Despite significant progress, the potential utilization of self-projected views from partial inputs and the effective reduction of noise in generated point clouds remain under-explored. In this paper, we propose a novel point cloud completion method that leverages self-projected view augmentation and implicit field constraints. Specifically, we introduce a cross-view augmentation (CVA) module and a cross-modal fusion (CMF) module to enhance information interaction and integration at the image and modality levels, respectively. We also propose a bidirection-aware refinement block to improve detail and completeness by considering both complete-to-partial detail perception and partial-to-complete structure perception paths. Additionally, we address the issue of noise reduction from the perspective of implicit field constraints. We evaluate our method on several baseline datasets, including PCN, ShapeNet55/34 and KITTI (car). Extensive experiments demonstrate that our method outperforms state-of-the-art methods, achieving improvements of 0.11 CD-l(1), 0.015 DCD and 0.009 F-score on the standard PCN test set. Furthermore, our approach effectively reduces noise in the generated point clouds, showcasing its promising potential for practical applications. |
| 分类号 | 一类 |
| WOS关键词 | INTERPOLATION ; DISTANCE |
| 资助项目 | National Natural Science Foundation of China[62376100] ; Natural Science Foundation of Guangdong Province of China[2022A1515010114] |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001398275700018 |
| 资助机构 | National Natural Science Foundation of China ; Natural Science Foundation of Guangdong Province of China |
| 其他责任者 | Kang, Wenxiong |
| 源URL | [http://dspace.imech.ac.cn/handle/311007/98237]  |
| 专题 | 力学研究所_流固耦合系统力学重点实验室(2012-) |
| 作者单位 | 1.Chinese Acad Sci, Inst Mech, Key Lab Mech Fluid Solid Coupling Syst, Beijing 100190, Peoples R China 2.Pazhou Lab, Guangzhou 510335, Peoples R China; 3.South China Univ Technol, Sch Future Technol, Guangzhou 510641, Peoples R China; 4.Nanyang Technol Univ, Coll Comp & Data Sci, Singapore 639798, Singapore; 5.South China Univ Technol, Sch Automat Sci & Engn, Guangzhou 510641, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Xiao, Haihong,He, Ying,Liu, Hao,et al. Point Cloud Completion via Self-Projected View Augmentation and Implicit Field Constraint[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2024,34(11):11564-11578. |
| APA | Xiao, Haihong,He, Ying,Liu, Hao,Kang, Wenxiong,&李玉琼.(2024).Point Cloud Completion via Self-Projected View Augmentation and Implicit Field Constraint.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,34(11),11564-11578. |
| MLA | Xiao, Haihong,et al."Point Cloud Completion via Self-Projected View Augmentation and Implicit Field Constraint".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 34.11(2024):11564-11578. |
入库方式： OAI收割
来源：力学研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。