Learning 2D Triangular Meshes from Images with Transformers

dc.contributor.authorZöch, Maximilian
dc.contributor.authorKrispel, Ulrich
dc.contributor.authorAugsdörfer, Ursula
dc.contributor.editorSkala, Václav
dc.date.accessioned2025-07-30T09:24:46Z
dc.date.available2025-07-30T09:24:46Z
dc.date.issued2025
dc.description.abstract-translatedIn this work, we present a method for learning 2D triangular meshes from images using the Transformer architecture. Creating polygonal representations of 2D surfaces from images has a wide range of applications, e.g. texture mapping and image segmentation. Current machine learning based methods either rely on deforming template meshes with fixed topology or require expensive post-processing to extract a planar polygonal mesh. In this paper, we demonstrate that deep learning can be utilized to directly generate a planar polygonal surface from arbitrary images without the need for additional input or constraints. Specifically, we show that the attention mechanism in transformer networks is highly effective in learning a unified representation of vertex positions and their neighborhood relationships. To showcase this, we propose a self-supervised training pipeline that enables end-to-end learning of meshes directly from images. We apply our approach to various datasets of handwritten letters and digits, and show that the model is capable of learning meshes with varying genus.en
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.doihttp://www.doi.org/10.24132/CSRN.2025-11
dc.identifier.issn2464-4617 (Print)
dc.identifier.issn2464-4625 (online)
dc.identifier.urihttp://hdl.handle.net/11025/62217
dc.language.isoenen
dc.publisherVaclav Skala - UNION Agencyen
dc.rights© Vaclav Skala - UNION Agencyen
dc.rights.accessopenAccessen
dc.subjectgenerování polygonových sítícs
dc.subjectstrojové učenícs
dc.subjecttransformátorové sítěcs
dc.subject.translatedpolygon mesh generationen
dc.subject.translatedmachine learningen
dc.subject.translatedtransformer networksen
dc.titleLearning 2D Triangular Meshes from Images with Transformersen
dc.typekonferenční příspěvekcs
dc.typeconferenceObjecten
dc.type.statusPeer revieweden
dc.type.versionpublishedVersionen
local.files.count1*
local.files.size3041060*
local.has.filesyes*

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
B23.pdf
Size:
2.9 MB
Format:
Adobe Portable Document Format
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: