MDSSN: An end-to-end deep network on triangle mesh parameterization.
Saved in:
| Title: | MDSSN: An end-to-end deep network on triangle mesh parameterization. |
|---|---|
| Authors: | Hu, Ruihan1 (AUTHOR) rh.hu@hit.edu.cn, Tang, Zhi-Ri2 (AUTHOR), Yang, Rui3 (AUTHOR), Wang, Zhongjie1 (AUTHOR) |
| Source: | Knowledge-Based Systems. Jan2024, Vol. 284, pN.PAG-N.PAG. 1p. |
| Subjects: | Convolutional neural networks, Computer vision, Deep learning, Mesh networks, Block designs |
| Abstract: | Mesh data plays a crucial role in a wide range of applications worldwide within the field of 3D computer vision. In contrast to traditional Euclidean space arrangements, meshes encompass spatial information, including edges, faces, angles, and graph structures that embed face information within the mesh data. Nevertheless, conventional deep learning frameworks such as convolutional neural networks (CNNs) have struggled to achieve significant advancements in handling meshes. This paper proposes a simple mesh computation framework called Mesh Decomposition Second-order Sobolev Network (MDSSN) to model triangle meshes and represent their shape. The construction of face-based Riemannian and edge-based Riemannian graphs is motivated by the remarkable representation capabilities of edges and faces in mesh data, achieved through a graph composition mechanism. Furthermore, we design end-to-end operators, including the Sobolev-filter block, pooling, and unpooling blocks, which draw inspiration from traditional deep learning frameworks for modeling the mesh structure. Importantly, the design of the mesh-filter block incorporates the second-order Sobolev metric. To address common challenges in mesh classification and segmentation tasks, we have designed dedicated classification and segmentation modules. We utilize a joint loss function that integrates losses from adjacent faces and categories. We evaluate the performance of the MDSSN in mesh classification and segmentation tasks, focusing on its ability to represent 3D shapes. Experimental results demonstrate that MDSSN achieves superior performance compared to other state-of-the-art approaches. [ABSTRACT FROM AUTHOR] |
| Copyright of Knowledge-Based Systems is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 174708223 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: MDSSN: An end-to-end deep network on triangle mesh parameterization. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Hu%2C+Ruihan%22">Hu, Ruihan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> rh.hu@hit.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Tang%2C+Zhi-Ri%22">Tang, Zhi-Ri</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yang%2C+Rui%22">Yang, Rui</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Zhongjie%22">Wang, Zhongjie</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Knowledge-Based+Systems%22">Knowledge-Based Systems</searchLink>. Jan2024, Vol. 284, pN.PAG-N.PAG. 1p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Mesh+networks%22">Mesh networks</searchLink><br /><searchLink fieldCode="DE" term="%22Block+designs%22">Block designs</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Mesh data plays a crucial role in a wide range of applications worldwide within the field of 3D computer vision. In contrast to traditional Euclidean space arrangements, meshes encompass spatial information, including edges, faces, angles, and graph structures that embed face information within the mesh data. Nevertheless, conventional deep learning frameworks such as convolutional neural networks (CNNs) have struggled to achieve significant advancements in handling meshes. This paper proposes a simple mesh computation framework called Mesh Decomposition Second-order Sobolev Network (MDSSN) to model triangle meshes and represent their shape. The construction of face-based Riemannian and edge-based Riemannian graphs is motivated by the remarkable representation capabilities of edges and faces in mesh data, achieved through a graph composition mechanism. Furthermore, we design end-to-end operators, including the Sobolev-filter block, pooling, and unpooling blocks, which draw inspiration from traditional deep learning frameworks for modeling the mesh structure. Importantly, the design of the mesh-filter block incorporates the second-order Sobolev metric. To address common challenges in mesh classification and segmentation tasks, we have designed dedicated classification and segmentation modules. We utilize a joint loss function that integrates losses from adjacent faces and categories. We evaluate the performance of the MDSSN in mesh classification and segmentation tasks, focusing on its ability to represent 3D shapes. Experimental results demonstrate that MDSSN achieves superior performance compared to other state-of-the-art approaches. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Knowledge-Based Systems is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=174708223 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.knosys.2023.111177 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 1 StartPage: N.PAG Subjects: – SubjectFull: Convolutional neural networks Type: general – SubjectFull: Computer vision Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Mesh networks Type: general – SubjectFull: Block designs Type: general Titles: – TitleFull: MDSSN: An end-to-end deep network on triangle mesh parameterization. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Hu, Ruihan – PersonEntity: Name: NameFull: Tang, Zhi-Ri – PersonEntity: Name: NameFull: Yang, Rui – PersonEntity: Name: NameFull: Wang, Zhongjie IsPartOfRelationships: – BibEntity: Dates: – D: 25 M: 01 Text: Jan2024 Type: published Y: 2024 Identifiers: – Type: issn-print Value: 09507051 Numbering: – Type: volume Value: 284 Titles: – TitleFull: Knowledge-Based Systems Type: main |
| ResultId | 1 |
