Show simple item record

dc.contributor.authorLi, Yuanen_US
dc.contributor.authorHe, Xiangyangen_US
dc.contributor.authorJiang, Yankaien_US
dc.contributor.authorLiu, Huanen_US
dc.contributor.authorTao, Yuboen_US
dc.contributor.authorHai, Linen_US
dc.contributor.editorUmetani, Nobuyukien_US
dc.contributor.editorWojtan, Chrisen_US
dc.contributor.editorVouga, Etienneen_US
dc.date.accessioned2022-10-04T06:39:28Z
dc.date.available2022-10-04T06:39:28Z
dc.date.issued2022
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14655
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14655
dc.description.abstractGraph transformer has achieved remarkable success in graph-based segmentation tasks. Inspired by this success, we propose a novel method named MeshFormer for applying the graph transformer to the semantic segmentation of high-resolution meshes. The main challenges are the large data size, the massive model size, and the insufficient extraction of high-resolution semantic meanings. The large data or model size necessitates unacceptably extensive computational resources, and the insufficient semantic meanings lead to inaccurate segmentation results. MeshFormer addresses these three challenges with three components. First, a boundary-preserving simplification is introduced to reduce the data size while maintaining the critical high-resolution information in segmentation boundaries. Second, a Ricci flow-based clustering algorithm is presented for constructing hierarchical structures of meshes, replacing many convolutions layers for global support with only a few convolutions in hierarchy structures. In this way, the model size can be reduced to an acceptable range. Third, we design a graph transformer with cross-resolution convolutions, which extracts richer high-resolution semantic meanings and improves segmentation results over previous methods. Experiments show that MeshFormer achieves gains from 1.0% to 5.8% on artificial and real-world datasets.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies ! Neural networks; Shape analysis
dc.subjectComputing methodologies ! Neural networks
dc.subjectShape analysis
dc.titleMeshFormer: High-resolution Mesh Segmentation with Graph Transformeren_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersCurves and Meshes
dc.description.volume41
dc.description.number7
dc.identifier.doi10.1111/cgf.14655
dc.identifier.pages37-49
dc.identifier.pages13 pages


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • 41-Issue 7
    Pacific Graphics 2022 - Symposium Proceedings

Show simple item record