NNWarp: Neural Network-Based Nonlinear Deformation

NNWarp is a highly re-usable and efficient neural network (NN) based nonlinear deformable simulation framework. Unlike other machine learning applications such as image recognition, where different inputs have a uniform and consistent format (e.g., an array of all the pixels in an image), the input...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on visualization and computer graphics Ročník 26; číslo 4; s. 1745 - 1759
Hlavní autoři: Luo, Ran, Shao, Tianjia, Wang, Huamin, Xu, Weiwei, Chen, Xiang, Zhou, Kun, Yang, Yin
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.04.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:1077-2626, 1941-0506, 1941-0506
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract NNWarp is a highly re-usable and efficient neural network (NN) based nonlinear deformable simulation framework. Unlike other machine learning applications such as image recognition, where different inputs have a uniform and consistent format (e.g., an array of all the pixels in an image), the input for deformable simulation is quite variable, high-dimensional, and parametrization-unfriendly. Consequently, even though the neural network is known for its rich expressivity of nonlinear functions, directly using an NN to reconstruct the force-displacement relation for general deformable simulation is nearly impossible. NNWarp obviates this difficulty by partially restoring the force-displacement relation via warping the nodal displacement simulated using a simplistic constitutive model-the linear elasticity. In other words, NNWarp yields an incremental displacement fix per mesh node based on a simplified (therefore incorrect) simulation result other than synthesizing the unknown displacement directly. We introduce a compact yet effective feature vector including geodesic , potential and digression to sort training pairs of per-node linear and nonlinear displacement. NNWarp is robust under different model shapes and tessellations. With the assistance of deformation substructuring, one NN training is able to handle a wide range of 3D models of various geometries. Thanks to the linear elasticity and its constant system matrix, the underlying simulator only needs to perform one pre-factorized matrix solve at each time step, which allows NNWarp to simulate large models in real time.
AbstractList NNWarp is a highly re-usable and efficient neural network (NN) based nonlinear deformable simulation framework. Unlike other machine learning applications such as image recognition, where different inputs have a uniform and consistent format (e.g., an array of all the pixels in an image), the input for deformable simulation is quite variable, high-dimensional, and parametrization-unfriendly. Consequently, even though the neural network is known for its rich expressivity of nonlinear functions, directly using an NN to reconstruct the force-displacement relation for general deformable simulation is nearly impossible. NNWarp obviates this difficulty by partially restoring the force-displacement relation via warping the nodal displacement simulated using a simplistic constitutive model–the linear elasticity. In other words, NNWarp yields an incremental displacement fix per mesh node based on a simplified (therefore incorrect) simulation result other than synthesizing the unknown displacement directly. We introduce a compact yet effective feature vector including geodesic , potential and digression to sort training pairs of per-node linear and nonlinear displacement. NNWarp is robust under different model shapes and tessellations. With the assistance of deformation substructuring, one NN training is able to handle a wide range of 3D models of various geometries. Thanks to the linear elasticity and its constant system matrix, the underlying simulator only needs to perform one pre-factorized matrix solve at each time step, which allows NNWarp to simulate large models in real time.
NNWarp is a highly re-usable and efficient neural network (NN) based nonlinear deformable simulation framework. Unlike other machine learning applications such as image recognition, where different inputs have a uniform and consistent format (e.g., an array of all the pixels in an image), the input for deformable simulation is quite variable, high-dimensional, and parametrization-unfriendly. Consequently, even though the neural network is known for its rich expressivity of nonlinear functions, directly using an NN to reconstruct the force-displacement relation for general deformable simulation is nearly impossible. NNWarp obviates this difficulty by partially restoring the force-displacement relation via warping the nodal displacement simulated using a simplistic constitutive model-the linear elasticity. In other words, NNWarp yields an incremental displacement fix per mesh node based on a simplified (therefore incorrect) simulation result other than synthesizing the unknown displacement directly. We introduce a compact yet effective feature vector including geodesic, potential and digression to sort training pairs of per-node linear and nonlinear displacement. NNWarp is robust under different model shapes and tessellations. With the assistance of deformation substructuring, one NN training is able to handle a wide range of 3D models of various geometries. Thanks to the linear elasticity and its constant system matrix, the underlying simulator only needs to perform one pre-factorized matrix solve at each time step, which allows NNWarp to simulate large models in real time.NNWarp is a highly re-usable and efficient neural network (NN) based nonlinear deformable simulation framework. Unlike other machine learning applications such as image recognition, where different inputs have a uniform and consistent format (e.g., an array of all the pixels in an image), the input for deformable simulation is quite variable, high-dimensional, and parametrization-unfriendly. Consequently, even though the neural network is known for its rich expressivity of nonlinear functions, directly using an NN to reconstruct the force-displacement relation for general deformable simulation is nearly impossible. NNWarp obviates this difficulty by partially restoring the force-displacement relation via warping the nodal displacement simulated using a simplistic constitutive model-the linear elasticity. In other words, NNWarp yields an incremental displacement fix per mesh node based on a simplified (therefore incorrect) simulation result other than synthesizing the unknown displacement directly. We introduce a compact yet effective feature vector including geodesic, potential and digression to sort training pairs of per-node linear and nonlinear displacement. NNWarp is robust under different model shapes and tessellations. With the assistance of deformation substructuring, one NN training is able to handle a wide range of 3D models of various geometries. Thanks to the linear elasticity and its constant system matrix, the underlying simulator only needs to perform one pre-factorized matrix solve at each time step, which allows NNWarp to simulate large models in real time.
Author Yang, Yin
Wang, Huamin
Zhou, Kun
Xu, Weiwei
Shao, Tianjia
Luo, Ran
Chen, Xiang
Author_xml – sequence: 1
  givenname: Ran
  orcidid: 0000-0003-2232-2775
  surname: Luo
  fullname: Luo, Ran
  email: luoran@unm.edu
  organization: Electrical and Computer Engineering Department, University of New Mexico, NM, USA
– sequence: 2
  givenname: Tianjia
  orcidid: 0000-0001-5485-3752
  surname: Shao
  fullname: Shao, Tianjia
  email: tianjiashao@gmail.com
  organization: School of Computing, University of Leeds, Leeds, United Kingdom
– sequence: 3
  givenname: Huamin
  surname: Wang
  fullname: Wang, Huamin
  email: whmin@cse.ohio-state.edu
  organization: Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA
– sequence: 4
  givenname: Weiwei
  surname: Xu
  fullname: Xu, Weiwei
  email: weiwei.xu.g@gmail.com
  organization: State Key Lab of CAD&CG, Zhejiang University, Hangzhou, Zhejiang, China
– sequence: 5
  givenname: Xiang
  orcidid: 0000-0002-6955-8729
  surname: Chen
  fullname: Chen, Xiang
  email: xchen.cs@gmail.com
  organization: State Key Lab of CAD&CG, Zhejiang University, Hangzhou, Zhejiang, China
– sequence: 6
  givenname: Kun
  orcidid: 0000-0003-4243-6112
  surname: Zhou
  fullname: Zhou, Kun
  email: kunzhou@acm.org
  organization: State Key Lab of CAD&CG, Zhejiang University, Hangzhou, Zhejiang, China
– sequence: 7
  givenname: Yin
  orcidid: 0000-0001-7645-5931
  surname: Yang
  fullname: Yang, Yin
  email: yangy@unm.edu
  organization: Electrical and Computer Engineering Department, University of New Mexico, NM, USA
BackLink https://www.ncbi.nlm.nih.gov/pubmed/30442607$$D View this record in MEDLINE/PubMed
BookMark eNp9kD1PwzAQhi1URMvHD0BIqBILS4rPdmyHDQoUJFSWCkbLcS5SII2LnQjx70lpYWBguhue99Xds08GjW-QkGOgEwCaXSyep7MJo6AnTGsQKeyQEWQCEppSOeh3qlTCJJNDsh_jK6UghM72yJBTIZikakTYfP5iw-pyPMcu2Lof7YcPb8m1jViM576pqwZtGN9g6cPStpVvDsluaeuIR9t5QBZ3t4vpffL4NHuYXj0mjousTcpCWEbLQikrnAAtRcZFbrnLXao4y6mTmEOa6VKmFEoHeVqgpRzyAkWG_ICcb2pXwb93GFuzrKLDurYN-i4aBjwFDpmGHj37g776LjT9cYZxxfpvtZI9dbqlunyJhVmFamnDp_mR0QNqA7jgYwxYGle13y-3wVa1AWrW2s1au1lrN1vtfRL-JH_K_8ucbDIVIv7yOuVSgOJfQxeK1w
CODEN ITVGEA
CitedBy_id crossref_primary_10_1145_3658154
crossref_primary_10_1016_j_media_2019_101569
crossref_primary_10_1109_TG_2023_3237943
crossref_primary_10_1007_s11390_021_1414_9
crossref_primary_10_1145_3386569_3392398
crossref_primary_10_1111_cgf_14128
Cites_doi 10.1145/37402.37427
10.1145/1073204.1073300
10.1109/TVCG.2012.173
10.1145/1618452.1618469
10.1109/ICCV.2015.357
10.1109/ISCSLP.2012.6423452
10.1145/2766910
10.1145/2601097.2601116
10.1109/TVCG.2005.13
10.1111/j.1467-8659.2012.03230.x
10.1109/CVPR.2014.223
10.1137/1011036
10.1016/j.neunet.2014.09.003
10.1145/2185520.2185566
10.1109/ICCV.2015.178
10.1145/1073204.1073296
10.1145/2461912.2462020
10.1145/3072959.3073685
10.1145/1882261.1866182
10.1145/3072959.3073608
10.1145/1618452.1618516
10.1109/TPAMI.2012.231
10.1111/j.1467-8659.2012.03031.x
10.1109/ICCV.2015.123
10.1145/3072959.3073643
10.1145/1778765.1778844
10.1145/2816795.2818129
10.1109/TVCG.2010.109
10.1145/2461912.2461931
10.1145/2343483.2343495
10.1145/2816795.2818063
10.1007/BF02551274
10.1145/3072959.3073631
10.1145/2766938
10.1145/2897824.2925979
10.1145/1731047.1731054
10.1145/74333.74355
10.1145/2980179.2980236
10.1145/2816795.2818090
10.1007/s11263-015-0816-y
10.1145/2508363.2508406
10.1145/3072959.3073655
10.1038/nature14236
10.1145/545261.545269
10.1145/2980179.2982437
10.1145/2508363.2508392
10.1145/2601097.2601136
10.1145/2816795.2818089
10.1145/2601097.2601217
10.1145/3083723
10.1145/1409060.1409118
10.1145/3072959.3073663
10.1145/2010324.1964988
10.1145/2343483.2343501
10.1016/0893-6080(91)90009-T
10.1145/2990496
10.1145/2766904
10.1145/2766911
10.1145/1882261.1866160
10.1145/1778765.1778776
10.1145/3072959.3073602
10.1145/1964921.1964986
10.1145/2893476
10.1109/TASL.2011.2134090
10.1145/1073204.1073216
10.1145/2010324.1964966
10.1145/1028523.1028541
10.1145/2231816.2231821
10.1145/2461912.2461961
10.1109/38.20317
10.1109/ICASSP.2013.6639081
10.1109/TPAMI.2015.2437384
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID 97E
RIA
RIE
AAYXX
CITATION
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
DOI 10.1109/TVCG.2018.2881451
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library (IEL)
CrossRef
PubMed
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitleList Technology Research Database

MEDLINE - Academic
PubMed
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1941-0506
EndPage 1759
ExternalDocumentID 30442607
10_1109_TVCG_2018_2881451
8536417
Genre orig-research
Journal Article
GrantInformation_xml – fundername: Microsoft Research Asia
  funderid: 10.13039/100006112
– fundername: NSFC
  grantid: 61732016
– fundername: NSFC
  grantid: 61772024; 61732016
– fundername: National Science Foundation
  grantid: CHS-1524992
  funderid: 10.13039/100000001
– fundername: NSFC
  grantid: 61772462; U1736217
– fundername: Fundamental Research Funds for the Central Universities
  grantid: 2017YFB1002600
  funderid: 10.13039/501100012226
– fundername: National Science Foundation
  grantid: CHS-1717972
  funderid: 10.13039/100000001
– fundername: AFRL
  grantid: FA9453-18-2-0022
– fundername: Alibaba IDEA Lab
GroupedDBID ---
-~X
.DC
0R~
29I
4.4
53G
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
IEDLZ
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
TN5
5VS
AAYXX
AETIX
AGSQL
AI.
AIBXA
ALLEH
CITATION
H~9
IFJZH
RNI
RZB
VH1
AAYOK
NPM
RIG
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
ID FETCH-LOGICAL-c349t-fd4a20fd77a4c41864934ba3cbc5732b0c6eb1598f6501fc1b5dea031bde49e3
IEDL.DBID RIE
ISICitedReferencesCount 31
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000519547200010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1077-2626
1941-0506
IngestDate Thu Sep 25 09:04:11 EDT 2025
Sun Jun 29 16:47:12 EDT 2025
Thu Apr 03 06:56:32 EDT 2025
Sat Nov 29 06:05:40 EST 2025
Tue Nov 18 21:42:11 EST 2025
Wed Aug 27 06:28:53 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 4
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c349t-fd4a20fd77a4c41864934ba3cbc5732b0c6eb1598f6501fc1b5dea031bde49e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0003-4243-6112
0000-0001-5485-3752
0000-0002-6955-8729
0000-0003-2232-2775
0000-0001-7645-5931
PMID 30442607
PQID 2372304876
PQPubID 75741
PageCount 15
ParticipantIDs ieee_primary_8536417
proquest_journals_2372304876
crossref_primary_10_1109_TVCG_2018_2881451
crossref_citationtrail_10_1109_TVCG_2018_2881451
pubmed_primary_30442607
proquest_miscellaneous_2135131981
PublicationCentury 2000
PublicationDate 2020-04-01
PublicationDateYYYYMMDD 2020-04-01
PublicationDate_xml – month: 04
  year: 2020
  text: 2020-04-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle IEEE transactions on visualization and computer graphics
PublicationTitleAbbrev TVCG
PublicationTitleAlternate IEEE Trans Vis Comput Graph
PublicationYear 2020
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
ref13
ref56
ref12
peng (ref39) 2017; 36
ref58
ref14
ref53
ref55
ref11
ref54
ref10
dechter (ref15) 1986
ref19
sharif razavian (ref16) 2014
wu (ref80) 2015
ref51
ref50
ref46
ref45
ref48
ref47
ref42
ref85
ref41
ref44
ref43
chen (ref22) 2016; abs 1606 915
abadi (ref82) 2016; abs 1603 4467
ref49
ref8
ref9
ref4
ref3
ref6
ref5
ref40
ref84
ref83
ref79
ref35
ref78
ref34
ref37
ref75
ref31
ref74
ref30
ref77
ref33
ref32
ref2
ref38
desbrun (ref52) 1999; 99
ref71
ref70
ref73
ref72
simonyan (ref17) 2014; abs 1409 1556
andrásfai (ref76) 1977
narain (ref59) 2016
ref68
ref24
ref67
ref23
ref26
ref69
ref25
ref64
ref20
ref63
kingma (ref81) 2014; abs 1412 6980
ref66
ref65
ref21
ref28
ref27
ref29
krizhevsky (ref18) 2012
kristan (ref7) 2015
bathe (ref1) 2008
liu (ref36) 2016; 35
ref60
ref62
ref61
References_xml – ident: ref48
  doi: 10.1145/37402.37427
– ident: ref64
  doi: 10.1145/1073204.1073300
– ident: ref73
  doi: 10.1109/TVCG.2012.173
– ident: ref66
  doi: 10.1145/1618452.1618469
– ident: ref6
  doi: 10.1109/ICCV.2015.357
– ident: ref5
  doi: 10.1109/ISCSLP.2012.6423452
– ident: ref35
  doi: 10.1145/2766910
– ident: ref10
  doi: 10.1145/2601097.2601116
– ident: ref13
  doi: 10.1109/TVCG.2005.13
– ident: ref83
  doi: 10.1111/j.1467-8659.2012.03230.x
– ident: ref20
  doi: 10.1109/CVPR.2014.223
– ident: ref72
  doi: 10.1137/1011036
– ident: ref2
  doi: 10.1016/j.neunet.2014.09.003
– volume: abs 1603 4467
  year: 2016
  ident: ref82
  article-title: Tensorflow: Large-scale machine learning on heterogeneous distributed systems
  publication-title: CoRR
– ident: ref70
  doi: 10.1145/2185520.2185566
– ident: ref23
  doi: 10.1109/ICCV.2015.178
– ident: ref50
  doi: 10.1145/1073204.1073296
– ident: ref31
  doi: 10.1145/2461912.2462020
– year: 1977
  ident: ref76
  publication-title: Introductory Graph Theory
– ident: ref43
  doi: 10.1145/3072959.3073685
– start-page: 21
  year: 2016
  ident: ref59
  article-title: Admm $\supseteq$? projective dynamics: Fast simulation of general constitutive models
  publication-title: Proc ACM SIGGRAPH/Eurographics Symp Comput Animation
– ident: ref55
  doi: 10.1145/1882261.1866182
– ident: ref79
  doi: 10.1145/3072959.3073608
– ident: ref33
  doi: 10.1145/1618452.1618516
– volume: abs 1409 1556
  year: 2014
  ident: ref17
  article-title: Very deep convolutional networks for large-scale image recognition
  publication-title: CoRR
– ident: ref19
  doi: 10.1109/TPAMI.2012.231
– ident: ref30
  doi: 10.1111/j.1467-8659.2012.03031.x
– ident: ref21
  doi: 10.1109/ICCV.2015.123
– ident: ref47
  doi: 10.1145/3072959.3073643
– ident: ref27
  doi: 10.1145/1778765.1778844
– ident: ref46
  doi: 10.1145/2816795.2818129
– ident: ref67
  doi: 10.1109/TVCG.2010.109
– start-page: 1912
  year: 2015
  ident: ref80
  article-title: 3d shapenets: A deep representation for volumetric shapes
  publication-title: Proc IEEE Conf Comput Vis Pattern Recognit
– year: 2008
  ident: ref1
  publication-title: Finite Element Method
– volume: abs 1412 6980
  year: 2014
  ident: ref81
  article-title: Adam: A method for stochastic optimization
  publication-title: CoRR
– start-page: 1
  year: 2015
  ident: ref7
  article-title: The visual object tracking vot2015 challenge results
  publication-title: Proc IEEE Int Conf Comput Vis Workshops
– ident: ref75
  doi: 10.1145/2461912.2461931
– start-page: 178
  year: 1986
  ident: ref15
  article-title: Learning while searching in constraint-satisfaction problems
  publication-title: Proc AAAI Nat Conf Artificial Intell
– ident: ref26
  doi: 10.1145/2343483.2343495
– ident: ref60
  doi: 10.1145/2816795.2818063
– ident: ref9
  doi: 10.1007/BF02551274
– ident: ref42
  doi: 10.1145/3072959.3073631
– ident: ref74
  doi: 10.1145/2766938
– ident: ref44
  doi: 10.1145/2897824.2925979
– ident: ref58
  doi: 10.1145/1731047.1731054
– start-page: 806
  year: 2014
  ident: ref16
  article-title: Cnn features off-the-shelf: An astounding baseline for recognition
  publication-title: Proc IEEE Conf Comp Vis Pattern Recognit
– ident: ref63
  doi: 10.1145/74333.74355
– ident: ref11
  doi: 10.1145/2980179.2980236
– ident: ref68
  doi: 10.1145/2816795.2818090
– ident: ref25
  doi: 10.1007/s11263-015-0816-y
– ident: ref53
  doi: 10.1145/2508363.2508406
– ident: ref78
  doi: 10.1145/3072959.3073655
– ident: ref37
  doi: 10.1038/nature14236
– ident: ref12
  doi: 10.1145/545261.545269
– ident: ref62
  doi: 10.1145/2980179.2982437
– ident: ref69
  doi: 10.1145/2508363.2508392
– ident: ref32
  doi: 10.1145/2601097.2601136
– ident: ref65
  doi: 10.1145/2816795.2818089
– ident: ref71
  doi: 10.1145/2601097.2601217
– ident: ref38
  doi: 10.1145/3083723
– ident: ref45
  doi: 10.1145/1409060.1409118
– ident: ref40
  doi: 10.1145/3072959.3073663
– ident: ref28
  doi: 10.1145/2010324.1964988
– ident: ref54
  doi: 10.1145/2343483.2343501
– volume: abs 1606 915
  year: 2016
  ident: ref22
  article-title: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFS
  publication-title: CoRR
– ident: ref8
  doi: 10.1016/0893-6080(91)90009-T
– ident: ref61
  doi: 10.1145/2990496
– ident: ref85
  doi: 10.1145/2766904
– ident: ref41
  doi: 10.1145/2766911
– ident: ref34
  doi: 10.1145/1882261.1866160
– ident: ref51
  doi: 10.1145/1778765.1778776
– start-page: 1097
  year: 2012
  ident: ref18
  article-title: Imagenet classification with deep convolutional neural networks
  publication-title: Proc Advances Neural Inf Process Syst
– volume: 36
  year: 2017
  ident: ref39
  article-title: Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning
  publication-title: ACM Trans Graph
  doi: 10.1145/3072959.3073602
– ident: ref14
  doi: 10.1145/1964921.1964986
– volume: 35
  year: 2016
  ident: ref36
  article-title: Guided learning of control graphs for physics-based characters
  publication-title: ACM Trans Graph
  doi: 10.1145/2893476
– ident: ref4
  doi: 10.1109/TASL.2011.2134090
– volume: 99
  year: 1999
  ident: ref52
  article-title: Interactive animation of structured deformable objects
  publication-title: Graph Interface
– ident: ref49
  doi: 10.1145/1073204.1073216
– ident: ref29
  doi: 10.1145/2010324.1964966
– ident: ref56
  doi: 10.1145/1028523.1028541
– ident: ref57
  doi: 10.1145/2231816.2231821
– ident: ref77
  doi: 10.1145/2461912.2461961
– ident: ref84
  doi: 10.1109/38.20317
– ident: ref3
  doi: 10.1109/ICASSP.2013.6639081
– ident: ref24
  doi: 10.1109/TPAMI.2015.2437384
SSID ssj0014489
Score 2.4781616
Snippet NNWarp is a highly re-usable and efficient neural network (NN) based nonlinear deformable simulation framework. Unlike other machine learning applications such...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1745
SubjectTerms Animation
Artificial neural networks
Computational modeling
Computer simulation
Constitutive models
data-driven animation
deformable model
Deformable models
Deformation
Displacement
Elasticity
Finite element method
Formability
Machine learning
Mathematical analysis
Mathematical models
Matrix methods
Neural network
Neural networks
nonlinear regression
Object recognition
Parameterization
physics-based simulation
Simulation
Strain
Substructuring
Three dimensional models
Training
Title NNWarp: Neural Network-Based Nonlinear Deformation
URI https://ieeexplore.ieee.org/document/8536417
https://www.ncbi.nlm.nih.gov/pubmed/30442607
https://www.proquest.com/docview/2372304876
https://www.proquest.com/docview/2135131981
Volume 26
WOSCitedRecordID wos000519547200010&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
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1941-0506
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014489
  issn: 1077-2626
  databaseCode: RIE
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwED-2IaIPfs2P6RwVfBKztWnWpL7pdPogxYcx91bSJAVBttFt_v1e2q4oqOBboZe0XC65u9zd7wAujSspahJBNOUJYUwZkqCVTSRKdCK1r0TeeW78zKNITCbhSw2uq1oYY0yefGa69jGP5euZWtmrsh6qloB5vA51zoOiVquKGKCbERb5hZxQtNLLCKbnhr3RePBok7hElwphO9NuwSZ68RabnX9TR3l_ld9NzVzlDHf_97N7sFOals5tIQv7UDPTA9j-AjjYBBpFrzKb3zgWkwNpoyIJnNyhLtNOVMBmyMy5N1VR4yGMhg-jwRMpuyYQ5bNwSVLNJHVTzblkinkiYKHPEumrRPW5TxNXBXg-90ORonHmpcpL-tpI3NuJNiw0_hE0prOpOQFHKtdIyT3TRx1mI3oWukd7TAfSRzssbYG75l2sSkRx29jiPc49CzeMLedjy_m45HwLrqoh8wJO4y_ipmVrRVhytAXt9QLF5YZbxNTn9nobz_YWXFSvcavY-IecmtkKaWw3QjxyBM58XCxsNfdaHk5__uYZbFHraOcpO21oLLOVOYcN9bF8W2QdlMeJ6OTy-AkkSdcn
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLZgIB4H3o_yLBInRFibpkvKjTeIUXGYYLcqTVIJCW1Tt_H7cdquAgmQuFWqk1aOE9ux_Rng2HiSoiYRRFOeEsaUISla2USiRKdSB0oUnede2jyORbcbPU_BaV0LY4wpks_MmX0sYvm6r8b2qqyJqqXFfD4NMyFj1CurteqYAToaUZlhyAlFO72KYfpe1Oy8XN3ZNC5xRoWwvWkXYA79eIvOzr8ppKLDyu_GZqF0bpf_97srsFQZl-5FKQ2rMGV6a7D4BXJwHWgcv8p8cO5aVA6kjcs0cHKJ2ky7cQmcIXP32tRljRvQub3pXN2Tqm8CUQGLRiTTTFIv05xLppgvWiwKWCoDlaqQBzT1VAtP6DASGZpnfqb8NNRG4u5OtWGRCTah0ev3zDa4UnlGSu6bELWYjelZ8B7tM92SAVpimQPehHeJqjDFbWuL96TwLbwosZxPLOeTivMOnNRDBiWgxl_E65atNWHFUQf2JguUVFtumNCA2wtuPN0dOKpf42axERDZM_0x0th-hHjoCJx5q1zYeu6JPOz8_M1DmL_vPLWT9kP8uAsL1LrdRQLPHjRG-djsw6z6GL0N84NCKj8BbujZhg
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=article&rft.atitle=NNWarp%3A+Neural+Network-Based+Nonlinear+Deformation&rft.jtitle=IEEE+transactions+on+visualization+and+computer+graphics&rft.au=Luo%2C+Ran&rft.au=Shao%2C+Tianjia&rft.au=Wang%2C+Huamin&rft.au=Xu%2C+Weiwei&rft.date=2020-04-01&rft.issn=1941-0506&rft.eissn=1941-0506&rft.volume=26&rft.issue=4&rft.spage=1745&rft_id=info:doi/10.1109%2FTVCG.2018.2881451&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-2626&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-2626&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-2626&client=summon