A Sparse Mesh Sampling Scheme for Graph-based Relief Pattern Classification

Simple item page
dc.contributor.authorPaolini, Gabrieleen_US
dc.contributor.authorGuiducci, Niccolòen_US
dc.contributor.authorTortorici, Claudioen_US
dc.contributor.authorBerretti, Stefanoen_US
dc.contributor.editorBanterle, Francescoen_US
dc.contributor.editorCaggianese, Giuseppeen_US
dc.contributor.editorCapece, Nicolaen_US
dc.contributor.editorErra, Ugoen_US
dc.contributor.editorLupinetti, Katiaen_US
dc.contributor.editorManfredi, Gildaen_US
dc.date.accessioned2023-11-12T15:37:39Z
dc.date.available2023-11-12T15:37:39Z
dc.date.issued2023
dc.description.abstractIn the context of geometric deep learning, the classification of relief patterns involves recognizing the surface characteristics of a 3D object, regardless of its global shape. State-of-the-art methods leverage powerful 2D deep learning image-based techniques by converting local patches of the surface into a texture image. However, their effectiveness is guaranteed only when the mesh is simple enough to allow this projection onto a 2D subspace. Therefore, developing deep learning techniques that can work directly on manifolds represents an interesting line of research for addressing these challenges. The objective of our paper is to extend and enhance the architecture described in a recent GNN approach for a relief pattern classifier through the introduction of a new sampling tecnhique for meshes. In their method, local mesh structures, referred to as SpiderPatches, are connected to form the nodes of a graph, called MeshGraph, that captures global structures of the mesh. These two data structures are then fed into a bi-level architecture based on Graph Attention Networks. The MeshGraph construction proves important in ensuring optimal classification results. By the proposed subsampling process, we tackle the problem of fine-tuning multiple hyperparameters inherent the MeshGraph by defining a graph structure that is aware of the mesh geometric details. We demonstrate that the graph constructed using this approach robustly captures the relief patterns on the surface, obviating the need for data augmentation during training. The resulting network is robust, easily customizable, and shows comparable performance to recent methods, all while operating directly on 3D data.en_US
dc.description.sectionheadersOptimizations for Computer Graphics
dc.description.seriesinformationSmart Tools and Applications in Graphics - Eurographics Italian Chapter Conference
dc.identifier.doi10.2312/stag.20231298
dc.identifier.isbn978-3-03868-235-6
dc.identifier.issn2617-4855
dc.identifier.pages93-101
dc.identifier.pages9 pages
dc.identifier.urihttps://doi.org/10.2312/stag.20231298
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/stag20231298
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 -> Neural networks; Object identification
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.subjectObject identification
dc.titleA Sparse Mesh Sampling Scheme for Graph-based Relief Pattern Classificationen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
093-101.pdf
Size:
3.27 MB
Format:
Adobe Portable Document Format
Download
Collections
Italian Chapter Conference 2023 - Smart Tools and Apps in Graphics