Segmentation of CAD models using hybrid representation
In this paper, we introduce an innovative method for computer-aided design (CAD) segmentation by concatenating meshes and CAD models. Many previous CAD segmentation methods have achieved impressive performance using single representations, such as meshes, CAD, and point clouds. However, existing met...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2025-04-01
|
| Series: | Virtual Reality & Intelligent Hardware |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2096579625000014 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850146131020873728 |
|---|---|
| author | Claude Uwimana Shengdi Zhou Limei Yang Zhuqing Li Norbelt Mutagisha Edouard Niyongabo Bin Zhou |
| author_facet | Claude Uwimana Shengdi Zhou Limei Yang Zhuqing Li Norbelt Mutagisha Edouard Niyongabo Bin Zhou |
| author_sort | Claude Uwimana |
| collection | DOAJ |
| description | In this paper, we introduce an innovative method for computer-aided design (CAD) segmentation by concatenating meshes and CAD models. Many previous CAD segmentation methods have achieved impressive performance using single representations, such as meshes, CAD, and point clouds. However, existing methods cannot effectively combine different three-dimensional model types for the direct conversion, alignment, and integrity maintenance of geometric and topological information. Hence, we propose an integration approach that combines the geometric accuracy of CAD data with the flexibility of mesh representations, as well as introduce a unique hybrid representation that combines CAD and mesh models to enhance segmentation accuracy. To combine these two model types, our hybrid system utilizes advanced-neural-network techniques to convert CAD models into mesh models. For complex CAD models, model segmentation is crucial for model retrieval and reuse. In partial retrieval, it aims to segment a complex CAD model into several simple components. The first component of our hybrid system involves advanced mesh-labeling algorithms that harness the digitization of CAD properties to mesh models. The second component integrates labelled face features for CAD segmentation by leveraging the abundant multisemantic information embedded in CAD models. This combination of mesh and CAD not only refines the accuracy of boundary delineation but also provides a comprehensive understanding of the underlying object semantics. This study uses the Fusion 360 Gallery dataset. Experimental results indicate that our hybrid method can segment these models with higher accuracy than other methods that use single representations. |
| format | Article |
| id | doaj-art-8db2756903d8461eb61c0475f9dfdcb2 |
| institution | OA Journals |
| issn | 2096-5796 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Virtual Reality & Intelligent Hardware |
| spelling | doaj-art-8db2756903d8461eb61c0475f9dfdcb22025-08-20T02:27:55ZengKeAi Communications Co., Ltd.Virtual Reality & Intelligent Hardware2096-57962025-04-017218820210.1016/j.vrih.2025.01.001Segmentation of CAD models using hybrid representationClaude Uwimana0Shengdi Zhou1Limei Yang2Zhuqing Li3Norbelt Mutagisha4Edouard Niyongabo5Bin Zhou6State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing 100191, ChinaState Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing 100191, ChinaChina Aerospace Systems Engineering Corporation, Beijing 100070, ChinaState Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing 100191, China; Peace-Bay Academy of Virtual Reality, Shenyang 110004, ChinaDepartment of Signal and Information Processing, Beihang University, Beijing 100191, ChinaDepartment of Computer Science, University of Sherbrooke, Sherbrooke J1C0A1, CanadaState Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing 100191, China; Peace-Bay Academy of Virtual Reality, Shenyang 110004, China; Corresponding author.In this paper, we introduce an innovative method for computer-aided design (CAD) segmentation by concatenating meshes and CAD models. Many previous CAD segmentation methods have achieved impressive performance using single representations, such as meshes, CAD, and point clouds. However, existing methods cannot effectively combine different three-dimensional model types for the direct conversion, alignment, and integrity maintenance of geometric and topological information. Hence, we propose an integration approach that combines the geometric accuracy of CAD data with the flexibility of mesh representations, as well as introduce a unique hybrid representation that combines CAD and mesh models to enhance segmentation accuracy. To combine these two model types, our hybrid system utilizes advanced-neural-network techniques to convert CAD models into mesh models. For complex CAD models, model segmentation is crucial for model retrieval and reuse. In partial retrieval, it aims to segment a complex CAD model into several simple components. The first component of our hybrid system involves advanced mesh-labeling algorithms that harness the digitization of CAD properties to mesh models. The second component integrates labelled face features for CAD segmentation by leveraging the abundant multisemantic information embedded in CAD models. This combination of mesh and CAD not only refines the accuracy of boundary delineation but also provides a comprehensive understanding of the underlying object semantics. This study uses the Fusion 360 Gallery dataset. Experimental results indicate that our hybrid method can segment these models with higher accuracy than other methods that use single representations.http://www.sciencedirect.com/science/article/pii/S2096579625000014B-RepNethybrid segmentationCAD modelsclassificationMeshCNNMeshCAD-Net |
| spellingShingle | Claude Uwimana Shengdi Zhou Limei Yang Zhuqing Li Norbelt Mutagisha Edouard Niyongabo Bin Zhou Segmentation of CAD models using hybrid representation Virtual Reality & Intelligent Hardware B-RepNet hybrid segmentation CAD models classification MeshCNN MeshCAD-Net |
| title | Segmentation of CAD models using hybrid representation |
| title_full | Segmentation of CAD models using hybrid representation |
| title_fullStr | Segmentation of CAD models using hybrid representation |
| title_full_unstemmed | Segmentation of CAD models using hybrid representation |
| title_short | Segmentation of CAD models using hybrid representation |
| title_sort | segmentation of cad models using hybrid representation |
| topic | B-RepNet hybrid segmentation CAD models classification MeshCNN MeshCAD-Net |
| url | http://www.sciencedirect.com/science/article/pii/S2096579625000014 |
| work_keys_str_mv | AT claudeuwimana segmentationofcadmodelsusinghybridrepresentation AT shengdizhou segmentationofcadmodelsusinghybridrepresentation AT limeiyang segmentationofcadmodelsusinghybridrepresentation AT zhuqingli segmentationofcadmodelsusinghybridrepresentation AT norbeltmutagisha segmentationofcadmodelsusinghybridrepresentation AT edouardniyongabo segmentationofcadmodelsusinghybridrepresentation AT binzhou segmentationofcadmodelsusinghybridrepresentation |