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

Botsch, Jan; Hardik, Jain; Hellwich, Olaf

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

dc.contributor.author	Botsch, Jan
dc.contributor.author	Hardik, Jain
dc.contributor.author	Hellwich, Olaf
dc.date.accessioned	2022-05-05T14:29:46Z
dc.date.available	2022-05-05T14:29:46Z
dc.date.issued	2022
dc.description.abstract	In 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.sponsorship	DFG, 414044773, Open Access Publizieren 2021 - 2022 / Technische Universität Berlin	en
dc.identifier.eissn	2169-3536
dc.identifier.uri	https://depositonce.tu-berlin.de/handle/11303/16796
dc.identifier.uri	http://dx.doi.org/10.14279/depositonce-15574
dc.language.iso	en	en
dc.rights.uri	https://creativecommons.org/licenses/by/4.0/	en
dc.subject.ddc	004 Datenverarbeitung; Informatik	de
dc.subject.other	3D surface mesh	en
dc.subject.other	faces	en
dc.subject.other	deep learning	en
dc.subject.other	icosahedral CNN	en
dc.subject.other	mesh denoising network	en
dc.subject.other	noise filtering	en
dc.subject.other	spherical parametrization	en
dc.subject.other	U-net	en
dc.title	IMD-Net: A deep learning-based icosahedral mesh denoising network	en
dc.type	Article	en
dc.type.version	publishedVersion	en
dcterms.bibliographicCitation.doi	10.1109/ACCESS.2022.3164714	en
dcterms.bibliographicCitation.journaltitle	IEEE access	en
dcterms.bibliographicCitation.originalpublishername	IEEE	en
dcterms.bibliographicCitation.originalpublisherplace	New York, NY	en
dcterms.bibliographicCitation.pageend	38649	en
dcterms.bibliographicCitation.pagestart	38635	en
dcterms.bibliographicCitation.volume	10	en
tub.accessrights.dnb	free	en
tub.affiliation	Fak. 2 Mathematik und Naturwissenschaften::Inst. Mathematik::FG Differentialgleichungen	de
tub.affiliation	Fak. 4 Elektrotechnik und Informatik::Inst. Technische Informatik und Mikroelektronik::FG Computer Vision & Remote Sensing	de
tub.affiliation.faculty	Fak. 2 Mathematik und Naturwissenschaften	de
tub.affiliation.faculty	Fak. 4 Elektrotechnik und Informatik	de
tub.affiliation.group	FG Differentialgleichungen	de
tub.affiliation.group	FG Computer Vision & Remote Sensing	de
tub.affiliation.institute	Inst. Mathematik	de
tub.affiliation.institute	Inst. Technische Informatik und Mikroelektronik	de
tub.publisher.universityorinstitution	Technische Universität Berlin	en

Files

Original bundle

Now showing 1 - 1 of 1

Name:: IMD-Net_A_Deep_Learning-Based_Icosahedral_Mesh_Denoising_Network.pdf
Size:: 6.15 MB
Format:: Adobe Portable Document Format
Description:

Download

License bundle

Now showing 1 - 1 of 1

Name:: license.txt
Size:: 4.86 KB
Format:: Item-specific license agreed upon to submission
Description:

Download

Collections

Publications