Fast and Robust Non-Rigid Registration Using Accelerated Majorization-Minimization

Non-rigid 3D registration, which deforms a source 3D shape in a non-rigid way to align with a target 3D shape, is a classical problem in computer vision. Such problems can be challenging because of imperfect data (noise, outliers and partial overlap) and high degrees of freedom. Existing methods typ...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on pattern analysis and machine intelligence Ročník 45; číslo 8; s. 9681 - 9698
Hlavní autoři:	Yao, Yuxin, Deng, Bailin, Xu, Weiwei, Zhang, Juyong
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.08.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Acceleration Algorithms Alignment Anderson acceleration Computer vision Convergence Deformable models Deformation Error analysis Iterative methods non-rigid registration Optimization Outliers (statistics) Registration Regularization robust estimator Robustness Shape Smoothness Software Solvers Source code Three-dimensional displays welsch's function
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Non-rigid 3D registration, which deforms a source 3D shape in a non-rigid way to align with a target 3D shape, is a classical problem in computer vision. Such problems can be challenging because of imperfect data (noise, outliers and partial overlap) and high degrees of freedom. Existing methods typically adopt the <inline-formula><tex-math notation="LaTeX">\ell _{p}</tex-math> <mml:math><mml:msub><mml:mi>ℓ</mml:mi><mml:mi>p</mml:mi></mml:msub></mml:math><inline-graphic xlink:href="zhang-ieq1-3247603.gif"/> </inline-formula> type robust norm to measure the alignment error and regularize the smoothness of deformation, and use a proximal algorithm to solve the resulting non-smooth optimization problem. However, the slow convergence of such algorithms limits their wide applications. In this paper, we propose a formulation for robust non-rigid registration based on a globally smooth robust norm for alignment and regularization, which can effectively handle outliers and partial overlaps. The problem is solved using the majorization-minimization algorithm, which reduces each iteration to a convex quadratic problem with a closed-form solution. We further apply Anderson acceleration to speed up the convergence of the solver, enabling the solver to run efficiently on devices with limited compute capability. Extensive experiments demonstrate the effectiveness of our method for non-rigid alignment between two shapes with outliers and partial overlaps, with quantitative evaluation showing that it outperforms state-of-the-art methods in terms of registration accuracy and computational speed. The source code is available at https://github.com/yaoyx689/AMM_NRR .
AbstractList	Non-rigid 3D registration, which deforms a source 3D shape in a non-rigid way to align with a target 3D shape, is a classical problem in computer vision. Such problems can be challenging because of imperfect data (noise, outliers and partial overlap) and high degrees of freedom. Existing methods typically adopt the <inline-formula><tex-math notation="LaTeX">\ell _{p}</tex-math> <mml:math><mml:msub><mml:mi>ℓ</mml:mi><mml:mi>p</mml:mi></mml:msub></mml:math><inline-graphic xlink:href="zhang-ieq1-3247603.gif"/> </inline-formula> type robust norm to measure the alignment error and regularize the smoothness of deformation, and use a proximal algorithm to solve the resulting non-smooth optimization problem. However, the slow convergence of such algorithms limits their wide applications. In this paper, we propose a formulation for robust non-rigid registration based on a globally smooth robust norm for alignment and regularization, which can effectively handle outliers and partial overlaps. The problem is solved using the majorization-minimization algorithm, which reduces each iteration to a convex quadratic problem with a closed-form solution. We further apply Anderson acceleration to speed up the convergence of the solver, enabling the solver to run efficiently on devices with limited compute capability. Extensive experiments demonstrate the effectiveness of our method for non-rigid alignment between two shapes with outliers and partial overlaps, with quantitative evaluation showing that it outperforms state-of-the-art methods in terms of registration accuracy and computational speed. The source code is available at https://github.com/yaoyx689/AMM_NRR . Non-rigid 3D registration, which deforms a source 3D shape in a non-rigid way to align with a target 3D shape, is a classical problem in computer vision. Such problems can be challenging because of imperfect data (noise, outliers and partial overlap) and high degrees of freedom. Existing methods typically adopt the [Formula Omitted] type robust norm to measure the alignment error and regularize the smoothness of deformation, and use a proximal algorithm to solve the resulting non-smooth optimization problem. However, the slow convergence of such algorithms limits their wide applications. In this paper, we propose a formulation for robust non-rigid registration based on a globally smooth robust norm for alignment and regularization, which can effectively handle outliers and partial overlaps. The problem is solved using the majorization-minimization algorithm, which reduces each iteration to a convex quadratic problem with a closed-form solution. We further apply Anderson acceleration to speed up the convergence of the solver, enabling the solver to run efficiently on devices with limited compute capability. Extensive experiments demonstrate the effectiveness of our method for non-rigid alignment between two shapes with outliers and partial overlaps, with quantitative evaluation showing that it outperforms state-of-the-art methods in terms of registration accuracy and computational speed. The source code is available at https://github.com/yaoyx689/AMM_NRR . Non-rigid 3D registration, which deforms a source 3D shape in a non-rigid way to align with a target 3D shape, is a classical problem in computer vision. Such problems can be challenging because of imperfect data (noise, outliers and partial overlap) and high degrees of freedom. Existing methods typically adopt the l type robust norm to measure the alignment error and regularize the smoothness of deformation, and use a proximal algorithm to solve the resulting non-smooth optimization problem. However, the slow convergence of such algorithms limits their wide applications. In this paper, we propose a formulation for robust non-rigid registration based on a globally smooth robust norm for alignment and regularization, which can effectively handle outliers and partial overlaps. The problem is solved using the majorization-minimization algorithm, which reduces each iteration to a convex quadratic problem with a closed-form solution. We further apply Anderson acceleration to speed up the convergence of the solver, enabling the solver to run efficiently on devices with limited compute capability. Extensive experiments demonstrate the effectiveness of our method for non-rigid alignment between two shapes with outliers and partial overlaps, with quantitative evaluation showing that it outperforms state-of-the-art methods in terms of registration accuracy and computational speed. The source code is available at https://github.com/yaoyx689/AMM_NRR. Non-rigid 3D registration, which deforms a source 3D shape in a non-rigid way to align with a target 3D shape, is a classical problem in computer vision. Such problems can be challenging because of imperfect data (noise, outliers and partial overlap) and high degrees of freedom. Existing methods typically adopt the lp type robust norm to measure the alignment error and regularize the smoothness of deformation, and use a proximal algorithm to solve the resulting non-smooth optimization problem. However, the slow convergence of such algorithms limits their wide applications. In this paper, we propose a formulation for robust non-rigid registration based on a globally smooth robust norm for alignment and regularization, which can effectively handle outliers and partial overlaps. The problem is solved using the majorization-minimization algorithm, which reduces each iteration to a convex quadratic problem with a closed-form solution. We further apply Anderson acceleration to speed up the convergence of the solver, enabling the solver to run efficiently on devices with limited compute capability. Extensive experiments demonstrate the effectiveness of our method for non-rigid alignment between two shapes with outliers and partial overlaps, with quantitative evaluation showing that it outperforms state-of-the-art methods in terms of registration accuracy and computational speed. The source code is available at https://github.com/yaoyx689/AMM_NRR.Non-rigid 3D registration, which deforms a source 3D shape in a non-rigid way to align with a target 3D shape, is a classical problem in computer vision. Such problems can be challenging because of imperfect data (noise, outliers and partial overlap) and high degrees of freedom. Existing methods typically adopt the lp type robust norm to measure the alignment error and regularize the smoothness of deformation, and use a proximal algorithm to solve the resulting non-smooth optimization problem. However, the slow convergence of such algorithms limits their wide applications. In this paper, we propose a formulation for robust non-rigid registration based on a globally smooth robust norm for alignment and regularization, which can effectively handle outliers and partial overlaps. The problem is solved using the majorization-minimization algorithm, which reduces each iteration to a convex quadratic problem with a closed-form solution. We further apply Anderson acceleration to speed up the convergence of the solver, enabling the solver to run efficiently on devices with limited compute capability. Extensive experiments demonstrate the effectiveness of our method for non-rigid alignment between two shapes with outliers and partial overlaps, with quantitative evaluation showing that it outperforms state-of-the-art methods in terms of registration accuracy and computational speed. The source code is available at https://github.com/yaoyx689/AMM_NRR.
Author	Deng, Bailin Yao, Yuxin Xu, Weiwei Zhang, Juyong
Author_xml	– sequence: 1 givenname: Yuxin orcidid: 0000-0002-5410-0782 surname: Yao fullname: Yao, Yuxin email: yaoyuxin@mail.ustc.edu.cn organization: School of Mathematical Sciences, University of Science and Technology of China, Hefei, China – sequence: 2 givenname: Bailin orcidid: 0000-0002-0158-7670 surname: Deng fullname: Deng, Bailin email: dengb3@cardiff.ac.uk organization: School of Computer Science and Informatics, Cardiff University, Cardiff, U.K – sequence: 3 givenname: Weiwei surname: Xu fullname: Xu, Weiwei email: xww@cad.zju.edu.cn organization: Department of Computer science, State Key Lab of CAD & CG, Zhejiang University, Hangzhou, China – sequence: 4 givenname: Juyong orcidid: 0000-0002-1805-1426 surname: Zhang fullname: Zhang, Juyong email: juyong@ustc.edu.cn organization: School of Mathematical Sciences, University of Science and Technology of China, Hefei, China
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/37027610$$D View this record in MEDLINE/PubMed
BookMark	eNp9kUFrGzEQhUVIie0kf6CUstBLL-uORutd6WhC0xrspDjJWWi1s0bGltLV7iH99VVsB0oOPUkafW-YeW_Czn3wxNhHDlPOQX17_DVfLaYIKKYCi6oEccbGyEvIFSo8Z2PgJeZSohyxSYxbAF7MQFywkagAq5LDmK1vTewz45tsHeohXe-Cz9du41KBNi72neld8NlTdH6Tza2lHaUSNdnKbEPn_hy-85Xzbn96XLEPrdlFuj6dl-zh9vvjzc98ef9jcTNf5lbMsM9Jtbxp0WBNhbVtbVRjjUEhoDWF4ZKMqKWpK2ol1ljxVnFlLRQNillJ4pJ9PXZ97sLvgWKv9y6m6XbGUxiixkrJKtnERUK_vEO3Yeh8mk2jFHwGkkOZqM8naqj31Ojnzu1N96LfvEqAPAK2CzF21Grr-sPGySS30xz0ayz6EIt-jUWfYklSfCd96_5f0aejyBHRPwIoVIWF-AuvG5jy
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_1016_j_eswa_2025_126524 crossref_primary_10_1016_j_knosys_2023_111280 crossref_primary_10_3390_aerospace11100859 crossref_primary_10_1109_TPAMI_2025_3560297 crossref_primary_10_1111_cgf_15230 crossref_primary_10_1111_cgf_70035 crossref_primary_10_1016_j_cag_2024_103972 crossref_primary_10_1109_TCSVT_2024_3447044 crossref_primary_10_1016_j_dsp_2025_105545 crossref_primary_10_1093_bjr_tqae067
Cites_doi	10.1109/CVPR42600.2020.00496 10.1145/1399504.1360696 10.1111/cgf.14502 10.1109/TSP.2014.2388434 10.1142/S1793536911000829 10.1109/ICME.2019.00061 10.1109/CVPR.2015.7299115 10.1145/3355089.3356491 10.1145/1516522.1516526 10.1002/nla.617 10.1109/CVPR.2014.491 10.1111/cgf.12699 10.1109/TIP.2019.2909197 10.1007/978-3-642-15558-1_26 10.1145/2517967 10.1145/321296.321305 10.1109/TPAMI.2010.223 10.1080/03610927708827533 10.1109/TVCG.2018.2832136 10.1145/3197517.3201290 10.1109/CVPR.2018.00761 10.1137/130919398 10.1007/s00371-019-01670-1 10.1002/cpa.20303 10.1109/ICCV.2015.353 10.1109/CVPR.2011.5995438 10.1145/2601097.2601165 10.1137/1.9781611974409 10.1109/TPAMI.2022.3164653 10.1109/CVPR42600.2020.00142 10.1109/ICCV.2009.5459161 10.1137/19M1245384 10.1109/CVPR.2015.7298631 10.1111/j.1467-8659.2008.01282.x 10.1109/CVPR.2007.383165 10.1109/TPAMI.2019.2915229 10.1109/TVCG.2012.310 10.1109/ICCV.2005.17 10.1109/ICCV.2015.236 10.1109/TVCG.2018.2816926 10.1561/2200000016 10.1109/3DV.2019.00013 10.1109/ICCV.2017.104 10.1145/2897824.2925930 10.1109/CVPR52688.2022.00547 10.1109/CVPR46437.2021.01016 10.1109/CVPR42600.2020.00762 10.1109/TPAMI.2020.2971687 10.1007/978-3-030-58548-8_15 10.1145/1276377.1276478 10.1073/pnas.0508601103 10.1109/TPAMI.2010.46 10.1145/1618452.1618521 10.1109/ICRA.2018.8461063 10.1137/10078356X 10.1109/TPAMI.2019.2940655 10.1111/cgf.12178 10.1111/cgf.14081 10.1109/CVPR.2012.6247673
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
DOI	10.1109/TPAMI.2023.3247603
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 PubMed MEDLINE - Academic
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 Computer Science
EISSN	2160-9292 1939-3539
EndPage	9698
ExternalDocumentID	37027610 10_1109_TPAMI_2023_3247603 10049724
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 62122071; 62272433 funderid: 10.13039/501100001809 – fundername: Fundamental Research Funds for the Central Universities grantid: WK3470000021 funderid: 10.13039/501100012226
GroupedDBID	--- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E 9M8 AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ADRHT AENEX AETEA AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P FA8 HZ~ H~9 IBMZZ ICLAB IEDLZ IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNI RNS RXW RZB TAE TN5 UHB VH1 XJT ~02 AAYXX CITATION NPM RIG 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c352t-e9f1df2a2be4ccfba9dcaa2330fa4a18ea3b8ab7ef82b271f919cc04d2356e3
IEDL.DBID	RIE
ISICitedReferencesCount	14
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001022958600027&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0162-8828 1939-3539
IngestDate	Sat Sep 27 19:41:38 EDT 2025 Sun Nov 30 04:33:29 EST 2025 Mon Jul 21 05:27:55 EDT 2025 Sat Nov 29 02:58:23 EST 2025 Tue Nov 18 20:53:11 EST 2025 Wed Aug 27 02:03:57 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	8
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-c352t-e9f1df2a2be4ccfba9dcaa2330fa4a18ea3b8ab7ef82b271f919cc04d2356e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-5410-0782 0000-0002-0158-7670 0000-0002-1805-1426
PMID	37027610
PQID	2831508106
PQPubID	85458
PageCount	18
ParticipantIDs	proquest_journals_2831508106 crossref_primary_10_1109_TPAMI_2023_3247603 crossref_citationtrail_10_1109_TPAMI_2023_3247603 ieee_primary_10049724 pubmed_primary_37027610 proquest_miscellaneous_2798711013
PublicationCentury	2000
PublicationDate	2023-08-01
PublicationDateYYYYMMDD	2023-08-01
PublicationDate_xml	– month: 08 year: 2023 text: 2023-08-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev	TPAMI
PublicationTitleAlternate	IEEE Trans Pattern Anal Mach Intell
PublicationYear	2023
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	ref13 ref57 ref15 ref59 ref14 ref58 ref53 ref52 ref11 ref55 ref10 ref54 ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref48 li (ref66) 2022 ref47 ref42 ref44 boži? (ref41) 2020 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 guennebaud (ref60) 2010 ref40 zhang (ref12) 2022; 44 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref1 ref39 ref38 boži? (ref43) 2020 ref24 ref23 ref67 ref26 andriy (ref25) 2010; 32 bronstein (ref62) 2008 moenning (ref56) 2003 ref64 ref63 ref22 ref21 ref65 ref28 ref27 ref29 wand (ref20) 2007 ref61
References_xml	– year: 2008 ident: ref62 publication-title: Numerical Geometry of Non-Rigid Shapes – ident: ref42 doi: 10.1109/CVPR42600.2020.00496 – ident: ref57 doi: 10.1145/1399504.1360696 – year: 2003 ident: ref56 article-title: Fast marching farthest point sampling – ident: ref18 doi: 10.1111/cgf.14502 – start-page: 18727 year: 2020 ident: ref43 article-title: Neural non-rigid tracking publication-title: Proc Int Conf Neural Inf Process – ident: ref31 doi: 10.1109/TSP.2014.2388434 – ident: ref38 doi: 10.1142/S1793536911000829 – ident: ref23 doi: 10.1109/ICME.2019.00061 – ident: ref10 doi: 10.1109/CVPR.2015.7299115 – ident: ref52 doi: 10.1145/3355089.3356491 – ident: ref30 doi: 10.1145/1516522.1516526 – year: 2010 ident: ref60 article-title: Eigen v3 – ident: ref50 doi: 10.1002/nla.617 – ident: ref61 doi: 10.1109/CVPR.2014.491 – ident: ref4 doi: 10.1111/cgf.12699 – ident: ref24 doi: 10.1109/TIP.2019.2909197 – ident: ref63 doi: 10.1007/978-3-642-15558-1_26 – ident: ref64 doi: 10.1145/2517967 – ident: ref14 doi: 10.1145/321296.321305 – ident: ref29 doi: 10.1109/TPAMI.2010.223 – ident: ref9 doi: 10.1080/03610927708827533 – ident: ref5 doi: 10.1109/TVCG.2018.2832136 – ident: ref51 doi: 10.1145/3197517.3201290 – ident: ref35 doi: 10.1109/CVPR.2018.00761 – ident: ref48 doi: 10.1137/130919398 – ident: ref6 doi: 10.1007/s00371-019-01670-1 – ident: ref59 doi: 10.1002/cpa.20303 – ident: ref7 doi: 10.1109/ICCV.2015.353 – ident: ref22 doi: 10.1109/CVPR.2011.5995438 – ident: ref32 doi: 10.1145/2601097.2601165 – ident: ref13 doi: 10.1137/1.9781611974409 – volume: 44 start-page: 3450 year: 2022 ident: ref12 article-title: Fast and robust iterative closest point publication-title: IEEE Trans Pattern Anal Mach Intell – ident: ref67 doi: 10.1109/TPAMI.2022.3164653 – ident: ref36 doi: 10.1109/CVPR42600.2020.00142 – ident: ref21 doi: 10.1109/ICCV.2009.5459161 – ident: ref49 doi: 10.1137/19M1245384 – ident: ref33 doi: 10.1109/CVPR.2015.7298631 – ident: ref2 doi: 10.1111/j.1467-8659.2008.01282.x – ident: ref1 doi: 10.1109/CVPR.2007.383165 – ident: ref46 doi: 10.1109/TPAMI.2019.2915229 – year: 2022 ident: ref66 article-title: Non-rigid point cloud registration with neural deformation pyramid – ident: ref17 doi: 10.1109/TVCG.2012.310 – ident: ref28 doi: 10.1109/ICCV.2005.17 – ident: ref39 doi: 10.1109/ICCV.2015.236 – ident: ref11 doi: 10.1109/TVCG.2018.2816926 – ident: ref8 doi: 10.1561/2200000016 – ident: ref40 doi: 10.1109/3DV.2019.00013 – ident: ref34 doi: 10.1109/ICCV.2017.104 – ident: ref55 doi: 10.1145/2897824.2925930 – ident: ref65 doi: 10.1109/CVPR52688.2022.00547 – ident: ref44 doi: 10.1109/CVPR46437.2021.01016 – ident: ref16 doi: 10.1109/CVPR42600.2020.00762 – ident: ref26 doi: 10.1109/TPAMI.2020.2971687 – ident: ref47 doi: 10.1007/978-3-030-58548-8_15 – ident: ref19 doi: 10.1145/1276377.1276478 – ident: ref37 doi: 10.1073/pnas.0508601103 – volume: 32 start-page: 2262 year: 2010 ident: ref25 article-title: Point set registration: Coherent point drift publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2010.46 – ident: ref3 doi: 10.1145/1618452.1618521 – ident: ref54 doi: 10.1109/ICRA.2018.8461063 – ident: ref15 doi: 10.1137/10078356X – ident: ref45 doi: 10.1109/TPAMI.2019.2940655 – ident: ref58 doi: 10.1111/cgf.12178 – ident: ref53 doi: 10.1111/cgf.14081 – ident: ref27 doi: 10.1109/CVPR.2012.6247673 – start-page: 7002 year: 2020 ident: ref41 article-title: DeepDeform: Learning non-rigid RGB-D reconstruction with semi-supervised data publication-title: Proc IEEE Conf Comput Vis and Pattern Recog – start-page: 49 year: 2007 ident: ref20 article-title: Reconstruction of deforming geometry from time-varying point clouds publication-title: Proc 5th Eurographics Symp Geometry Process
SSID	ssj0014503
Score	2.5443616
Snippet	Non-rigid 3D registration, which deforms a source 3D shape in a non-rigid way to align with a target 3D shape, is a classical problem in computer vision. Such...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	9681
SubjectTerms	Acceleration Algorithms Alignment Anderson acceleration Computer vision Convergence Deformable models Deformation Error analysis Iterative methods non-rigid registration Optimization Outliers (statistics) Registration Regularization robust estimator Robustness Shape Smoothness Software Solvers Source code Three-dimensional displays welsch's function
Title	Fast and Robust Non-Rigid Registration Using Accelerated Majorization-Minimization
URI	https://ieeexplore.ieee.org/document/10049724 https://www.ncbi.nlm.nih.gov/pubmed/37027610 https://www.proquest.com/docview/2831508106 https://www.proquest.com/docview/2798711013
Volume	45
WOSCitedRecordID	wos001022958600027&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: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB7RigMcaCkFFtoqSNxQtonzcHxcIVbtYVfV0sPeIj_GVRAkaB_9_R07TrSXInFzEsexMjOZ-WLPfABfUStGbtjEPNeMAAqpscqwiI2xstRFZRBzTzbBl8tqvRZ3IVnd58Igot98hlPX9Gv5ptN796vs2lU3E5zlR3DEedkna41LBnnhaZAphCETJxwxZMgk4vr-bra4nTqi8CnFD7xMHHtOxgmRlS5z9sAheYaV54NN73TmJ_853VN4E6LLaNarw1t4ge0ZnAzMDVEw5DN4fVCG8B2s5nK7i2RrolWn9tRcdm28ah4aOoEPY2XdyG8viGZak6tyFSZMtJC_uk3I5IwXTdv8CQfn8HP-4_77TRy4FmJNIdguRmFTY5lkCnOtrZLCaClZliVW5jKtUGaqkoqjrZhiPLUiFVonuWFZUWL2Ho7brsWPEInCitJokaKqciU54S_HWVUKLsvcJmYC6fC6ax3KkDs2jN-1hyOJqL20aietOkhrAt_Ge_72RTj-2fvcyeKgZy-GCVwMYq2DoW5riq5cRXwCxhP4Ml4mE3PrJrLFbk99uCBYSd8uGvpDrw7j4IMWfXrmoZ_hlZtbv2XwAo53mz1ewkv9uGu2myvS43V15fX4CR6B7Wk
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB5BQQIOFEqBhQJB4oayzcOJ4-MKsWpFd1Ute-gt8mNcBUGC9sHvZ-w40V6KxM1JHMfKzGTmiz3zAXxCrTJywybmTGcEUEiNVY5FbIyVpS4qg8g82QRfLqubG3EdktV9Lgwi-s1nOHVNv5ZvOr13v8rOXXUzwTN2Hx4UjIBPn641LhqwwhMhUxBDRk5IYsiRScT5-nq2uJw6qvApRRC8TBx_Ts4Jk5Uud_bAJXmOlbvDTe925sf_OeFn8DTEl9GsV4jncA_bEzgeuBuiYMon8OSgEOELWM3ldhfJ1kSrTu2puezaeNXcNnQCb8faupHfYBDNtCZn5WpMmGghf3SbkMsZL5q2-RUOTuH7_Ov6y0Uc2BZiTUHYLkZhU2MzmSlkWlslhdFSZnmeWMlkWqHMVSUVR1tlKuOpFanQOmEmy4sS85dw1HYtvoZIFFaURosUVcWU5ITAHGtVKbgsmU3MBNLhddc6FCJ3fBg_aw9IElF7adVOWnWQ1gQ-j_f87stw_LP3qZPFQc9eDBM4G8RaB1Pd1hRfuZr4BI0n8HG8TEbmVk5ki92e-nBBwJK-XjT0q14dxsEHLXpzx0M_wKOL9eKqvrpcfnsLj908-w2EZ3C02-zxHTzUf3bNdvPea_NfBEXvyA
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=Fast+and+Robust+Non-Rigid+Registration+Using+Accelerated+Majorization-Minimization&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Yao%2C+Yuxin&rft.au=Deng%2C+Bailin&rft.au=Xu%2C+Weiwei&rft.au=Zhang%2C+Juyong&rft.date=2023-08-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0162-8828&rft.eissn=1939-3539&rft.volume=45&rft.issue=8&rft.spage=9681&rft_id=info:doi/10.1109%2FTPAMI.2023.3247603&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon