Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy
| Title: | Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy |
|---|---|
| Authors: | Zhao, Mingyang, Meng, Gaofeng, Yan, Dong-Ming |
| Publication Year: | 2025 |
| Collection: | Computer Science |
| Subject Terms: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence |
| More Details: | Non-rigid alignment of point clouds is crucial for scene understanding, reconstruction, and various computer vision and robotics tasks. Recent advancements in implicit deformation networks for non-rigid registration have significantly reduced the reliance on large amounts of annotated training data. However, existing state-of-the-art methods still face challenges in handling occlusion scenarios. To address this issue, this paper introduces an innovative unsupervised method called Occlusion-Aware Registration (OAR) for non-rigidly aligning point clouds. The key innovation of our method lies in the utilization of the adaptive correntropy function as a localized similarity measure, enabling us to treat individual points distinctly. In contrast to previous approaches that solely minimize overall deviations between two shapes, we combine unsupervised implicit neural representations with the maximum correntropy criterion to optimize the deformation of unoccluded regions. This effectively avoids collapsed, tearing, and other physically implausible results. Moreover, we present a theoretical analysis and establish the relationship between the maximum correntropy criterion and the commonly used Chamfer distance, highlighting that the correntropy-induced metric can be served as a more universal measure for point cloud analysis. Additionally, we introduce locally linear reconstruction to ensure that regions lacking correspondences between shapes still undergo physically natural deformations. Our method achieves superior or competitive performance compared to existing approaches, particularly when dealing with occluded geometries. We also demonstrate the versatility of our method in challenging tasks such as large deformations, shape interpolation, and shape completion under occlusion disturbances. Comment: [ICLR 2025] Project and code at: https://github.com/zikai1/OAReg |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2502.10704 |
| Accession Number: | edsarx.2502.10704 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2502.10704 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20250215&spage=&pages=&title=Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy&atitle=Occlusion-aware%20Non-Rigid%20Point%20Cloud%20Registration%20via%20Unsupervised%20Neural%20Deformation%20Correntropy&aulast=Zhao%2C%20Mingyang&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2502.10704 RelevancyScore: 1129 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1129.24206542969 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Zhao%2C+Mingyang%22">Zhao, Mingyang</searchLink><br /><searchLink fieldCode="AR" term="%22Meng%2C+Gaofeng%22">Meng, Gaofeng</searchLink><br /><searchLink fieldCode="AR" term="%22Yan%2C+Dong-Ming%22">Yan, Dong-Ming</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2025 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Computer+Vision+and+Pattern+Recognition%22">Computer Science - Computer Vision and Pattern Recognition</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Artificial+Intelligence%22">Computer Science - Artificial Intelligence</searchLink> – Name: Abstract Label: Description Group: Ab Data: Non-rigid alignment of point clouds is crucial for scene understanding, reconstruction, and various computer vision and robotics tasks. Recent advancements in implicit deformation networks for non-rigid registration have significantly reduced the reliance on large amounts of annotated training data. However, existing state-of-the-art methods still face challenges in handling occlusion scenarios. To address this issue, this paper introduces an innovative unsupervised method called Occlusion-Aware Registration (OAR) for non-rigidly aligning point clouds. The key innovation of our method lies in the utilization of the adaptive correntropy function as a localized similarity measure, enabling us to treat individual points distinctly. In contrast to previous approaches that solely minimize overall deviations between two shapes, we combine unsupervised implicit neural representations with the maximum correntropy criterion to optimize the deformation of unoccluded regions. This effectively avoids collapsed, tearing, and other physically implausible results. Moreover, we present a theoretical analysis and establish the relationship between the maximum correntropy criterion and the commonly used Chamfer distance, highlighting that the correntropy-induced metric can be served as a more universal measure for point cloud analysis. Additionally, we introduce locally linear reconstruction to ensure that regions lacking correspondences between shapes still undergo physically natural deformations. Our method achieves superior or competitive performance compared to existing approaches, particularly when dealing with occluded geometries. We also demonstrate the versatility of our method in challenging tasks such as large deformations, shape interpolation, and shape completion under occlusion disturbances.<br />Comment: [ICLR 2025] Project and code at: https://github.com/zikai1/OAReg – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2502.10704" linkWindow="_blank">http://arxiv.org/abs/2502.10704</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2502.10704 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2502.10704 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Computer Vision and Pattern Recognition Type: general – SubjectFull: Computer Science - Artificial Intelligence Type: general Titles: – TitleFull: Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Zhao, Mingyang – PersonEntity: Name: NameFull: Meng, Gaofeng – PersonEntity: Name: NameFull: Yan, Dong-Ming IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 02 Type: published Y: 2025 |
| ResultId | 1 |