A Style Transfer Network of Local Geometry for 3D Mesh Stylization

Simple item page
dc.contributor.authorKang, Hongyuanen_US
dc.contributor.authorDong, Xiaoen_US
dc.contributor.authorGuo, Xufeien_US
dc.contributor.authorCao, Juanen_US
dc.contributor.authorChen, Zhongguien_US
dc.contributor.editorChaine, Raphaëlleen_US
dc.contributor.editorDeng, Zhigangen_US
dc.contributor.editorKim, Min H.en_US
dc.date.accessioned2023-10-09T07:42:49Z
dc.date.available2023-10-09T07:42:49Z
dc.date.issued2023
dc.description.abstractStyle transfer of images develops rapidly, however, only a few studies focus on geometric style transfer on 3D models. In this paper, we propose a style learning network to synthesize local geometric textures with similar styles on source mesh, driven by specific mesh or image features. Our network modifies a source mesh by predicting the displacement of vertices along the normal direction to generate geometric details. To constrain the style of the source mesh to be consistent with a specific style mesh, we define a style loss on 2D projected images of two meshes based on a differentiable renderer. We extract a set of global and local features from multiple views of 3D models via a pre-trained VGG network, driving the deformation of the source mesh based on the style loss. Our network is flexible in style learning as it can extract features from meshes and images to guide geometric deformation. Experiments verify the robustness of the proposed network and show the outperforming results of transferring multiple styles to the source mesh. We also conduct experiments to analyze the effectiveness of network design.en_US
dc.description.sectionheadersDetails and Styles on 3D Models
dc.description.seriesinformationPacific Graphics Short Papers and Posters
dc.identifier.doi10.2312/pg.20231272
dc.identifier.isbn978-3-03868-234-9
dc.identifier.pages65-72
dc.identifier.pages8 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20231272
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/pg20231272
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies -> Shape analysis
dc.subjectComputing methodologies
dc.subjectShape analysis
dc.titleA Style Transfer Network of Local Geometry for 3D Mesh Stylizationen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
065-072.pdf
Size:
14.6 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2023 Short Papers and Posters