Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes

The analysis of deforming 3D surface meshes is accelerated by autoencoders since the low-dimensional embeddings can be used to visualize underlying dynamics. But, state-of-the-art mesh convolutional autoencoders require a fixed connectivity of all input meshes handled by the autoencoder. This is due...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings / IEEE Workshop on Applications of Computer Vision s. 2344 - 2353
Hlavní autori: Hahner, Sara, Garcke, Jochen
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.01.2022
Predmet:
ISSN:2642-9381
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract The analysis of deforming 3D surface meshes is accelerated by autoencoders since the low-dimensional embeddings can be used to visualize underlying dynamics. But, state-of-the-art mesh convolutional autoencoders require a fixed connectivity of all input meshes handled by the autoencoder. This is due to either the use of spectral convolutional layers or mesh dependent pooling operations. Therefore, the types of datasets that one can study are limited and the learned knowledge cannot be transferred to other datasets that exhibit similar behavior. To address this, we transform the discretization of the surfaces to semi-regular meshes that have a locally regular connectivity and whose meshing is hierarchical. This allows us to apply the same spatial convolutional filters to the local neighborhoods and to define a pooling operator that can be applied to every semi-regular mesh. We apply the same mesh autoencoder to different datasets and our reconstruction error is more than 50% lower than the error from state-of-the-art models, which have to be trained for every mesh separately. Additionally, we visualize the underlying dynamics of unseen mesh sequences with an autoencoder trained on different classes of meshes.
AbstractList The analysis of deforming 3D surface meshes is accelerated by autoencoders since the low-dimensional embeddings can be used to visualize underlying dynamics. But, state-of-the-art mesh convolutional autoencoders require a fixed connectivity of all input meshes handled by the autoencoder. This is due to either the use of spectral convolutional layers or mesh dependent pooling operations. Therefore, the types of datasets that one can study are limited and the learned knowledge cannot be transferred to other datasets that exhibit similar behavior. To address this, we transform the discretization of the surfaces to semi-regular meshes that have a locally regular connectivity and whose meshing is hierarchical. This allows us to apply the same spatial convolutional filters to the local neighborhoods and to define a pooling operator that can be applied to every semi-regular mesh. We apply the same mesh autoencoder to different datasets and our reconstruction error is more than 50% lower than the error from state-of-the-art models, which have to be trained for every mesh separately. Additionally, we visualize the underlying dynamics of unseen mesh sequences with an autoencoder trained on different classes of meshes.
Author Hahner, Sara
Garcke, Jochen
Author_xml – sequence: 1
  givenname: Sara
  surname: Hahner
  fullname: Hahner, Sara
  email: sara.hahner@scai.fraunhofer.de
  organization: Fraunhofer Center for Machine Learning and SCAI,Sankt Augustin,Germany
– sequence: 2
  givenname: Jochen
  surname: Garcke
  fullname: Garcke, Jochen
  organization: Fraunhofer Center for Machine Learning and SCAI,Sankt Augustin,Germany
BookMark eNotj8tKxDAUQKMoOB39Al3kBzrePJssS3V0YERwfCyH2N5opJNI0wr69Sq6OpvDgVOQg5giEnLGYMEY2POnunlUTCqz4MD5AoBL2CMF01pJsEzBPplxLXlphWFHpMj5DUBYZsWMrG4wv9ImxY_UT2NI0fW0nsaEsU0dDtSngW5wF8o7fJl6N9BfHzNNnl4E73HAONJN-MJ8TA696zOe_HNOHpaX9811ub69WjX1ugwcxFgy03GF0gktpFCi4wKNNNh2kmvrwTmnwXvXtVVbuWduJHc_a1Yz25rOMyHm5PSvGxBx-z6EnRs-t7YCbawV37mATlY
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/WACV51458.2022.00240
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 1665409150
9781665409155
EISSN 2642-9381
EndPage 2353
ExternalDocumentID 9706899
Genre orig-research
GroupedDBID 29G
29O
6IE
6IF
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i203t-18d25e4a3634353d23e848ecd4269f0aaa60ffadc7c7ab2842a1459619c8df133
IEDL.DBID RIE
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000800471202041&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:49:39 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-18d25e4a3634353d23e848ecd4269f0aaa60ffadc7c7ab2842a1459619c8df133
PageCount 10
ParticipantIDs ieee_primary_9706899
PublicationCentury 2000
PublicationDate 2022-Jan.
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: 2022-Jan.
PublicationDecade 2020
PublicationTitle Proceedings / IEEE Workshop on Applications of Computer Vision
PublicationTitleAbbrev WACV
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0039193
Score 2.3087518
Snippet The analysis of deforming 3D surface meshes is accelerated by autoencoders since the low-dimensional embeddings can be used to visualize underlying dynamics....
SourceID ieee
SourceType Publisher
StartPage 2344
SubjectTerms Computer architecture
Computer vision
Deep Learning -> Graph Neural Networks 3D Computer Vision; Deep Learning; Deep Learning -> Neural Generative Models; Autoencoders; GANs; Transfer; Few-shot; Semi- and Un- supervised Learning
Geometry
Shape
Three-dimensional displays
Transforms
Visualization
Title Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes
URI https://ieeexplore.ieee.org/document/9706899
WOSCitedRecordID wos000800471202041&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED2VioGpQIv4lgdGQpM4iZOxKlQgQVVRKN2qq30RkaBBSdqBX4-dmsLAwmZFthxdbL93F787gAsv1a-nkcvR4IHGQUEHAyInDSQJAylhndRnci-Gw3g6TUYNuNxoYYiovnxGV6ZZ_8tXuVyaUFk3EW6k_YMt2BIiWmu1vk9dnmgmYqVxnpt0X3r9ieYCobm95ZucnL4Jb_wqoFLjx6D1v5l3ofMjxGOjDcTsQYMW-9CyzJHZfVm24e6BylemB63sSsI31ltWuclSqahgmpmyMb1nzmNder5gpj-VLE_Zta2QUrFx9kllB54HN0_9W8cWSXAy3-WV48XKDylAHnHNfLjyOcVBTFIZjWrqImLkpikqKaTAuQYjH7VZEu03yVil2kM9gOYiX9AhMDfgaHSuc73rA49CFDIkQT6FEsPAmx9B21hm9rHOgzGzRjn--_EJ7BjTr8MVp9CsiiWdwbZcVVlZnNcf7wvD8psu
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFH5BNNETKhh_24NHJ1vXsu1IUAIRCBFEbqR0r2GJMrMNDv71tmOiBy_emqXNltd23_de-70HcOso_XkauSwNHsI4KMISDNFSTKJnIIXnSX0mPW8w8KfTYFiCu60WBhHzy2d4b5r5WX4Yy5UJldUDz25o_2AHdjlj1N6otb7_u26guUghjnPsoP7abE00G-Dm_hY1WTmpCXD8KqGSI0i78r93H0LtR4pHhluQOYISLo-hUnBHUuzMtArdPqYLogeti7Uk3khzlcUmT2WICdHclIzwPbKe8-LzCTH9MSWxIg9FjZSMjKJPTGvw0n4ctzpWUSbBiqjtZpbjh5QjE27D1dzHDamLPvNRhkalqmwhRMNWSoTSk56YaziiQpsl0J6T9EOlfdQTKC_jJZ4CsZkrjNJ1rvc9c5ALT3L0kCKXgjNnfgZVY5nZxyYTxqwwyvnfj29gvzPu92a97uDpAg7MNGyCF5dQzpIVXsGeXGdRmlznE_kFBsSedQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+%2F+IEEE+Workshop+on+Applications+of+Computer+Vision&rft.atitle=Mesh+Convolutional+Autoencoder+for+Semi-Regular+Meshes+of+Different+Sizes&rft.au=Hahner%2C+Sara&rft.au=Garcke%2C+Jochen&rft.date=2022-01-01&rft.pub=IEEE&rft.eissn=2642-9381&rft.spage=2344&rft.epage=2353&rft_id=info:doi/10.1109%2FWACV51458.2022.00240&rft.externalDocID=9706899