Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226500634> ?p ?o ?g. }
- W4226500634 endingPage "1690" @default.
- W4226500634 startingPage "1678" @default.
- W4226500634 abstract "Deep learning techniques have proven effective in many applications, but these implementations mostly apply to data in one or two dimensions. Handling 3D data is more challenging due to its irregularity and complexity, and there is a growing interest in adapting deep learning techniques to the 3D domain. A recent successful approach called MeshCNN consists of a set of convolutional and pooling operators applied to the edges of triangular meshes. While this approach produced superb results in classification and segmentation of 3D shapes, it can only be applied to edges of a mesh, which can constitute a disadvantage for applications where the focuses are other primitives of the mesh. In this study, we propose face-based and vertex-based operators for mesh convolutional networks. We design two novel architectures based on the MeshCNN network that can operate on faces and vertices of a mesh, respectively. We demonstrate that the proposed face-based architecture outperforms the original MeshCNN implementation in mesh classification and mesh segmentation, setting the new state of the art on benchmark datasets. In addition, we extend the vertex-based operator to fit in the Point2Mesh model for mesh reconstruction from clean, noisy, and incomplete point clouds. While no statistically significant performance improvements are observed, the model training and inference time are reduced by the proposed approach by 91% and 20%, respectively, as compared with the original Point2Mesh model." @default.
- W4226500634 created "2022-05-05" @default.
- W4226500634 creator A5046600167 @default.
- W4226500634 creator A5053641918 @default.
- W4226500634 creator A5065885350 @default.
- W4226500634 date "2023-03-01" @default.
- W4226500634 modified "2023-10-14" @default.
- W4226500634 title "Mesh Convolutional Networks With Face and Vertex Feature Operators" @default.
- W4226500634 cites W1626653188 @default.
- W4226500634 cites W1644641054 @default.
- W4226500634 cites W1798731418 @default.
- W4226500634 cites W2003940193 @default.
- W4226500634 cites W2052789583 @default.
- W4226500634 cites W2173201413 @default.
- W4226500634 cites W2518780089 @default.
- W4226500634 cites W2558748708 @default.
- W4226500634 cites W2565662353 @default.
- W4226500634 cites W2737081152 @default.
- W4226500634 cites W2738551266 @default.
- W4226500634 cites W2768814045 @default.
- W4226500634 cites W2891396148 @default.
- W4226500634 cites W2979750740 @default.
- W4226500634 cites W3008606616 @default.
- W4226500634 cites W3035133372 @default.
- W4226500634 cites W3044683644 @default.
- W4226500634 cites W3048496284 @default.
- W4226500634 cites W3080385371 @default.
- W4226500634 cites W3101027576 @default.
- W4226500634 cites W3109462203 @default.
- W4226500634 cites W3124193169 @default.
- W4226500634 cites W3124359805 @default.
- W4226500634 cites W4239890145 @default.
- W4226500634 doi "https://doi.org/10.1109/tvcg.2021.3129156" @default.
- W4226500634 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34793303" @default.
- W4226500634 hasPublicationYear "2023" @default.
- W4226500634 type Work @default.
- W4226500634 citedByCount "0" @default.
- W4226500634 crossrefType "journal-article" @default.
- W4226500634 hasAuthorship W4226500634A5046600167 @default.
- W4226500634 hasAuthorship W4226500634A5053641918 @default.
- W4226500634 hasAuthorship W4226500634A5065885350 @default.
- W4226500634 hasConcept C108583219 @default.
- W4226500634 hasConcept C11413529 @default.
- W4226500634 hasConcept C121332964 @default.
- W4226500634 hasConcept C121684516 @default.
- W4226500634 hasConcept C131979681 @default.
- W4226500634 hasConcept C132525143 @default.
- W4226500634 hasConcept C13280743 @default.
- W4226500634 hasConcept C135628077 @default.
- W4226500634 hasConcept C144024400 @default.
- W4226500634 hasConcept C153180895 @default.
- W4226500634 hasConcept C154945302 @default.
- W4226500634 hasConcept C181145010 @default.
- W4226500634 hasConcept C185798385 @default.
- W4226500634 hasConcept C205649164 @default.
- W4226500634 hasConcept C2776214188 @default.
- W4226500634 hasConcept C2779304628 @default.
- W4226500634 hasConcept C31487907 @default.
- W4226500634 hasConcept C36289849 @default.
- W4226500634 hasConcept C41008148 @default.
- W4226500634 hasConcept C70437156 @default.
- W4226500634 hasConcept C80444323 @default.
- W4226500634 hasConcept C80899671 @default.
- W4226500634 hasConcept C81363708 @default.
- W4226500634 hasConcept C89600930 @default.
- W4226500634 hasConcept C97355855 @default.
- W4226500634 hasConceptScore W4226500634C108583219 @default.
- W4226500634 hasConceptScore W4226500634C11413529 @default.
- W4226500634 hasConceptScore W4226500634C121332964 @default.
- W4226500634 hasConceptScore W4226500634C121684516 @default.
- W4226500634 hasConceptScore W4226500634C131979681 @default.
- W4226500634 hasConceptScore W4226500634C132525143 @default.
- W4226500634 hasConceptScore W4226500634C13280743 @default.
- W4226500634 hasConceptScore W4226500634C135628077 @default.
- W4226500634 hasConceptScore W4226500634C144024400 @default.
- W4226500634 hasConceptScore W4226500634C153180895 @default.
- W4226500634 hasConceptScore W4226500634C154945302 @default.
- W4226500634 hasConceptScore W4226500634C181145010 @default.
- W4226500634 hasConceptScore W4226500634C185798385 @default.
- W4226500634 hasConceptScore W4226500634C205649164 @default.
- W4226500634 hasConceptScore W4226500634C2776214188 @default.
- W4226500634 hasConceptScore W4226500634C2779304628 @default.
- W4226500634 hasConceptScore W4226500634C31487907 @default.
- W4226500634 hasConceptScore W4226500634C36289849 @default.
- W4226500634 hasConceptScore W4226500634C41008148 @default.
- W4226500634 hasConceptScore W4226500634C70437156 @default.
- W4226500634 hasConceptScore W4226500634C80444323 @default.
- W4226500634 hasConceptScore W4226500634C80899671 @default.
- W4226500634 hasConceptScore W4226500634C81363708 @default.
- W4226500634 hasConceptScore W4226500634C89600930 @default.
- W4226500634 hasConceptScore W4226500634C97355855 @default.
- W4226500634 hasIssue "3" @default.
- W4226500634 hasLocation W42265006341 @default.
- W4226500634 hasLocation W42265006342 @default.
- W4226500634 hasOpenAccess W4226500634 @default.
- W4226500634 hasPrimaryLocation W42265006341 @default.
- W4226500634 hasRelatedWork W1895390915 @default.
- W4226500634 hasRelatedWork W2517027266 @default.