IMD-Net: A deep learning-based icosahedral mesh denoising network

dc.contributor.authorBotsch, Jan
dc.contributor.authorHardik, Jain
dc.contributor.authorHellwich, Olaf
dc.date.accessioned2022-05-05T14:29:46Z
dc.date.available2022-05-05T14:29:46Z
dc.date.issued2022
dc.description.abstractIn this work, we propose a novel denoising technique, the icosahedral mesh denoising network (IMD-Net) for closed genus-0 meshes. IMD-Net is a deep neural network that produces a denoised mesh in a single end-to-end pass, preserving and emphasizing natural object features in the process. A preprocessing step, exploiting the homeomorphism between genus-0 mesh and sphere, remeshes an irregular mesh using the regular mesh structure of a frequency subdivided icosahedron. Enabled by gauge equivariant convolutional layers arranged in a residual U-net, IMD-Net denoises the remeshing invariant to global mesh transformations as well as local feature constellations and orientations, doing so with a computational complexity of traditional conv2D kernel. The network is equipped with carefully crafted loss function that leverages differences between positional, normal and curvature fields of target and noisy mesh in a numerically stable fashion. In a first, two large shape datasets commonly used in related fields, ABC and ShapeNetCore , are introduced to evaluate mesh denoising. IMD-Net’s competitiveness with existing state-of-the-art techniques is established using both metric evaluations and visual inspection of denoised models. Our code is publicly available at https://github.com/jjabo/IMD-Net.en
dc.description.sponsorshipDFG, 414044773, Open Access Publizieren 2021 - 2022 / Technische Universität Berlinen
dc.identifier.eissn2169-3536
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/16796
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-15574
dc.language.isoenen
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subject.ddc004 Datenverarbeitung; Informatikde
dc.subject.other3D surface meshen
dc.subject.otherfacesen
dc.subject.otherdeep learningen
dc.subject.othericosahedral CNNen
dc.subject.othermesh denoising networken
dc.subject.othernoise filteringen
dc.subject.otherspherical parametrizationen
dc.subject.otherU-neten
dc.titleIMD-Net: A deep learning-based icosahedral mesh denoising networken
dc.typeArticleen
dc.type.versionpublishedVersionen
dcterms.bibliographicCitation.doi10.1109/ACCESS.2022.3164714en
dcterms.bibliographicCitation.journaltitleIEEE accessen
dcterms.bibliographicCitation.originalpublishernameIEEEen
dcterms.bibliographicCitation.originalpublisherplaceNew York, NYen
dcterms.bibliographicCitation.pageend38649en
dcterms.bibliographicCitation.pagestart38635en
dcterms.bibliographicCitation.volume10en
tub.accessrights.dnbfreeen
tub.affiliationFak. 2 Mathematik und Naturwissenschaften>Inst. Mathematik>FG Differentialgleichungende
tub.affiliationFak. 4 Elektrotechnik und Informatik>Inst. Technische Informatik und Mikroelektronik>FG Computer Vision & Remote Sensingde
tub.affiliation.facultyFak. 2 Mathematik und Naturwissenschaftende
tub.affiliation.facultyFak. 4 Elektrotechnik und Informatikde
tub.affiliation.groupFG Differentialgleichungende
tub.affiliation.groupFG Computer Vision & Remote Sensingde
tub.affiliation.instituteInst. Mathematikde
tub.affiliation.instituteInst. Technische Informatik und Mikroelektronikde
tub.publisher.universityorinstitutionTechnische Universität Berlinen
Files
Original bundle
Now showing 1 - 1 of 1
Loading…
Thumbnail Image
Name:
IMD-Net_A_Deep_Learning-Based_Icosahedral_Mesh_Denoising_Network.pdf
Size:
6.15 MB
Format:
Adobe Portable Document Format
Description:
Collections