Deconstruct to reconstruct: an automated pipeline for parsing complex CT assemblies

Many technical products are assemblies formed from smaller, versatile building blocks. Deconstructing such assemblies is an industrially important problem and an inspiring challenge for machine learning approaches. For the first time, we present an effective and fully automated pipeline for parsing...

Full description

Saved in:

Bibliographic Details
Published in:	Machine vision and applications Vol. 37; no. 1; p. 8
Main Authors:	Lippmann, Peter, Remme, Roman, Hamprecht, Fred A.
Format:	Journal Article
Language:	English
Published:	Berlin/Heidelberg Springer Berlin Heidelberg 01.01.2026 Springer Nature B.V
Subjects:	Algorithms Annotations Assemblies Automation Aviation Communications Engineering Computed tomography Computer Science Datasets High resolution Image Processing and Computer Vision Localization Machine learning Medical imaging Networks Pattern Recognition Quality control Segments Complex assemblies 3D Object recognition Assembly reconstruction Computed tomography 3D Segmentation
ISSN:	0932-8092, 1432-1769
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Many technical products are assemblies formed from smaller, versatile building blocks. Deconstructing such assemblies is an industrially important problem and an inspiring challenge for machine learning approaches. For the first time, we present an effective and fully automated pipeline for parsing large-scale, complex 3D assemblies from computed tomography (CT) scans into their individual parts. We have generated and make available a high-quality dataset of simulated, physically accurate CT scans with ground truth annotations. It consists of seven high-resolution CT scans ( voxels) of different technical assemblies with up to 3600 parts, each annotated with instance and semantic labels. The parts strongly vary in size and sometimes differ in fine details only. Our pipeline successfully handles the high-resolution volumetric inputs (3–30 GB) and produces detailed reconstructions of complex assemblies. The pipeline combines a 3D deep boundary detection network trained only on simulated CT scans with efficient graph partitioning to segment the 3D scans. The predicted instance segments are matched and aligned with a known part catalog to form a set of candidate part poses. The subset of these proposals that jointly best reconstructs the assembly is found by solving an instance of the maximum weighted independent set problem. We demonstrate that our approach generalizes to different CT scan setups and yields promising results even on real CT scans. Our pipeline is applicable to models that include parts not seen during training, making our approach adaptable to real-world scenarios.
AbstractList	Many technical products are assemblies formed from smaller, versatile building blocks. Deconstructing such assemblies is an industrially important problem and an inspiring challenge for machine learning approaches. For the first time, we present an effective and fully automated pipeline for parsing large-scale, complex 3D assemblies from computed tomography (CT) scans into their individual parts. We have generated and make available a high-quality dataset of simulated, physically accurate CT scans with ground truth annotations. It consists of seven high-resolution CT scans ( voxels) of different technical assemblies with up to 3600 parts, each annotated with instance and semantic labels. The parts strongly vary in size and sometimes differ in fine details only. Our pipeline successfully handles the high-resolution volumetric inputs (3–30 GB) and produces detailed reconstructions of complex assemblies. The pipeline combines a 3D deep boundary detection network trained only on simulated CT scans with efficient graph partitioning to segment the 3D scans. The predicted instance segments are matched and aligned with a known part catalog to form a set of candidate part poses. The subset of these proposals that jointly best reconstructs the assembly is found by solving an instance of the maximum weighted independent set problem. We demonstrate that our approach generalizes to different CT scan setups and yields promising results even on real CT scans. Our pipeline is applicable to models that include parts not seen during training, making our approach adaptable to real-world scenarios. Many technical products are assemblies formed from smaller, versatile building blocks. Deconstructing such assemblies is an industrially important problem and an inspiring challenge for machine learning approaches. For the first time, we present an effective and fully automated pipeline for parsing large-scale, complex 3D assemblies from computed tomography (CT) scans into their individual parts. We have generated and make available a high-quality dataset of simulated, physically accurate CT scans with ground truth annotations. It consists of seven high-resolution CT scans ( $$\sim \! 2000^3$$ voxels) of different technical assemblies with up to 3600 parts, each annotated with instance and semantic labels. The parts strongly vary in size and sometimes differ in fine details only. Our pipeline successfully handles the high-resolution volumetric inputs (3–30 GB) and produces detailed reconstructions of complex assemblies. The pipeline combines a 3D deep boundary detection network trained only on simulated CT scans with efficient graph partitioning to segment the 3D scans. The predicted instance segments are matched and aligned with a known part catalog to form a set of candidate part poses. The subset of these proposals that jointly best reconstructs the assembly is found by solving an instance of the maximum weighted independent set problem. We demonstrate that our approach generalizes to different CT scan setups and yields promising results even on real CT scans. Our pipeline is applicable to models that include parts not seen during training, making our approach adaptable to real-world scenarios. Many technical products are assemblies formed from smaller, versatile building blocks. Deconstructing such assemblies is an industrially important problem and an inspiring challenge for machine learning approaches. For the first time, we present an effective and fully automated pipeline for parsing large-scale, complex 3D assemblies from computed tomography (CT) scans into their individual parts. We have generated and make available a high-quality dataset of simulated, physically accurate CT scans with ground truth annotations. It consists of seven high-resolution CT scans ( voxels) of different technical assemblies with up to 3600 parts, each annotated with instance and semantic labels. The parts strongly vary in size and sometimes differ in fine details only. Our pipeline successfully handles the high-resolution volumetric inputs (3–30 GB) and produces detailed reconstructions of complex assemblies. The pipeline combines a 3D deep boundary detection network trained only on simulated CT scans with efficient graph partitioning to segment the 3D scans. The predicted instance segments are matched and aligned with a known part catalog to form a set of candidate part poses. The subset of these proposals that jointly best reconstructs the assembly is found by solving an instance of the maximum weighted independent set problem. We demonstrate that our approach generalizes to different CT scan setups and yields promising results even on real CT scans. Our pipeline is applicable to models that include parts not seen during training, making our approach adaptable to real-world scenarios.
ArticleNumber	8
Author	Lippmann, Peter Remme, Roman Hamprecht, Fred A.
Author_xml	– sequence: 1 givenname: Peter surname: Lippmann fullname: Lippmann, Peter email: peter.lippmann@iwr.uni-heidelberg.de organization: IWR, Heidelberg University – sequence: 2 givenname: Roman surname: Remme fullname: Remme, Roman organization: IWR, Heidelberg University – sequence: 3 givenname: Fred A. surname: Hamprecht fullname: Hamprecht, Fred A. organization: IWR, Heidelberg University
BookMark	eNp9kE1LxDAQhoOs4O7qH_AU8FydfDWtN1k_YcGD6zmkabp0aZOatKD_3miFvXmaGXifmeFZoYXzziJ0SeCaAMibCEBYkQEVGRBJZCZO0JJwRjMi83KBllCmvoCSnqFVjAcA4FLyJXq7t8a7OIbJjHj0OBzHW6wd1tPoez3aGg_tYLvWWdz4gAcdYuv22Ph-6Own3uywjtH2VdfaeI5OG91Fe_FX1-j98WG3ec62r08vm7ttZigjImOQi_Sd4bLStDTQ0JLwoqJW1loy3VghNJXciJoLAbzRRZPzqpJlIU0tLLA1upr3DsF_TDaO6uCn4NJJxRJICClAphSdUyb4GINt1BDaXocvRUD9yFOzPJXkqV95SiSIzVBMYbe34bj6H-obgI5zsw
Cites_doi	10.1201/9781482277234-12 10.1016/j.cad.2018.09.002 10.1109/CVPR52688.2022.01135 10.1137/1.9781611975499.12 10.1016/j.patcog.2013.02.008 10.1007/978-3-642-23094-3_3 10.1007/978-3-030-58452-8_13 10.1080/16864360.2007.10738497 10.1109/CVPR.2019.00963 10.1109/ICCV.2017.26 10.1109/TPAMI.2020.2980827 10.1109/TRO.2020.3033695 10.1109/TIT.1982.1056489 10.1109/CVPR52688.2022.00823 10.23919/MVA.2017.7986888 10.1145/2739480.2754667 10.1109/CVPR.2012.6248074 10.1109/CVPR.2018.00472 10.1007/s41095-022-0296-2 10.1016/j.cad.2004.01.005 10.1016/j.patcog.2015.02.006 10.1007/s10878-006-9635-y 10.1109/CVPR.2013.175 10.1145/3355089.3356504 10.1109/3DV.2016.79 10.1145/571647.571648 10.1109/SMI.2008.4547955 10.1007/978-3-642-15561-1_11 10.1016/S0166-218X(01)00290-6 10.1145/2980179.2980238 10.1109/WACV48630.2021.00038 10.1016/j.neucom.2015.08.127 10.1007/978-3-319-24574-4_28 10.1016/j.patcog.2006.04.034 10.1007/978-3-319-46475-6_47 10.1109/CVPR42600.2020.00178 10.1109/CVPR.2018.00208 10.1023/B:VISI.0000029664.99615.94 10.1007/s11263-009-0257-6 10.1007/978-3-031-19815-1_6 10.1007/978-3-030-89543-3_51 10.1109/CVPR52729.2023.00827 10.12981/motif.356 10.1109/ICCV.2019.00905 10.1109/ROBOT.2009.5152473 10.1016/j.cirp.2014.05.011 10.15607/RSS.2009.V.021 10.1145/1122501.1122507 10.7554/eLife.57613 10.1109/CVPR.2019.00656 10.1145/3549932 10.1016/j.rcim.2020.102086 10.1007/BF01581239 10.1117/12.57955 10.1007/978-3-642-25382-9_2 10.1109/SMI.2004.1314502 10.1016/j.displa.2021.102053 10.1109/ICCV.2011.6126550 10.1109/CVPR46437.2021.00738 10.1109/CVPR.2010.5540108 10.1109/CVPR52688.2022.01539 10.1109/ICARSC55462.2022.9784795
ContentType	Journal Article
Copyright	The Author(s) 2025 The Author(s) 2025. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: The Author(s) 2025 – notice: The Author(s) 2025. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	C6C AAYXX CITATION
DOI	10.1007/s00138-025-01717-5
DatabaseName	Springer Nature OA Free Journals CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList	CrossRef
DeliveryMethod	fulltext_linktorsrc
Discipline	Applied Sciences Engineering Computer Science
EISSN	1432-1769
ExternalDocumentID	10_1007_s00138_025_01717_5
GrantInformation_xml	– fundername: Ruprecht-Karls-Universität Heidelberg (1026)
GroupedDBID	-~C .4S .86 .DC .VR 06D 0R~ 0VY 199 1N0 203 29M 2J2 2JN 2JY 2KG 2KM 2LR 2~H 30V 4.4 406 408 409 40D 40E 5GY 5VS 67Z 6NX 78A 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AAPKM AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN ABAKF ABBBX ABBRH ABBXA ABDBE ABDBF ABDZT ABECU ABFSG ABFTD ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABRTQ ABSXP ABTEG ABTHY ABTKH ABTMW ABWNU ABXPI ACAOD ACDTI ACGFS ACHSB ACHXU ACIWK ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACSTC ACZOJ ADHHG ADHIR ADIMF ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEFQL AEGAL AEGNC AEJHL AEJRE AEMSY AENEX AEOHA AEPYU AETLH AEVLU AEXYK AEZWR AFBBN AFDZB AFHIU AFLOW AFOHR AFQWF AFWTZ AFZKB AGAYW AGDGC AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHPBZ AHSBF AHWEU AHYZX AIAKS AIGIU AIIXL AILAN AITGF AIXLP AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARMRJ ASPBG ATHPR AVWKF AXYYD AYFIA AYJHY AZFZN B-. BA0 BGNMA BSONS C6C CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 EAP EBLON EBS EIOEI ESBYG ESX FEDTE FERAY FFXSO FIGPU FNLPD FRRFC FWDCC GGCAI GGRSB GJIRD GNWQR GQ7 GQ8 GXS HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I09 IHE IJ- IKXTQ ITM IWAJR IXC IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ KDC KOV LAS LLZTM M4Y MA- N9A NB0 NPVJJ NQJWS O93 O9G O9I O9J OAM P19 P9O PF0 PT4 PT5 QOK QOS R89 R9I RHV RNS ROL RPX RSV S16 S1Z S27 S3B SAP SCO SDH SDM SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 TSG TSK TSV TUC U2A UG4 UOJIU UTJUX VC2 W23 W48 WK8 YLTOR Z45 ZMTXR ~EX -Y2 1SB 28- 2P1 2VQ 5QI 8FE 8FG AAOBN AARHV AAYTO AAYXX ABJCF ABQSL ABULA ACBXY ACUHS ADHKG ADMLS AEBTG AEFIE AEKMD AFEXP AFFHD AFGCZ AFKRA AGGDS AGQPQ AJBLW ARAPS ARCSS B0M BBWZM BDATZ BENPR BGLVJ CAG CCPQU CITATION COF EAD EDO EJD EMK EPL FINBP FSGXE H13 HCIFZ I-F KOW L6V M7S N2Q NDZJH NU0 O9- P62 PHGZM PHGZT PQGLB PTHSS R4E RNI RZK S26 S28 SCJ SCLPG T16 TUS UZXMN VFIZW ZY4 ~8M
ID	FETCH-LOGICAL-c2315-3065176c47ba29c0f29148b2e7da73afe55a274c5d45504fa8f64bb7987cd5e03
IEDL.DBID	RSV
ISSN	0932-8092
IngestDate	Sat Nov 29 03:17:10 EST 2025 Thu Nov 27 01:07:27 EST 2025 Sat Nov 22 01:10:31 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	1
Keywords	Complex assemblies 3D Object recognition Assembly reconstruction Computed tomography 3D Segmentation
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c2315-3065176c47ba29c0f29148b2e7da73afe55a274c5d45504fa8f64bb7987cd5e03
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
OpenAccessLink	https://link.springer.com/10.1007/s00138-025-01717-5
PQID	3274111807
PQPubID	2043753
ParticipantIDs	proquest_journals_3274111807 crossref_primary_10_1007_s00138_025_01717_5 springer_journals_10_1007_s00138_025_01717_5
PublicationCentury	2000
PublicationDate	2026-01-01
PublicationDateYYYYMMDD	2026-01-01
PublicationDate_xml	– month: 01 year: 2026 text: 2026-01-01 day: 01
PublicationDecade	2020
PublicationPlace	Berlin/Heidelberg
PublicationPlace_xml	– name: Berlin/Heidelberg – name: New York
PublicationTitle	Machine vision and applications
PublicationTitleAbbrev	Machine Vision and Applications
PublicationYear	2026
Publisher	Springer Berlin Heidelberg Springer Nature B.V
Publisher_xml	– name: Springer Berlin Heidelberg – name: Springer Nature B.V
References	1717_CR43 1717_CR45 DG Lowe (1717_CR39) 2004; 60 1717_CR46 1717_CR48 L De Chiffre (1717_CR3) 2014; 63 1717_CR49 CY Ip (1717_CR41) 2007; 4 S Qi (1717_CR47) 2021; 69 J-L Shih (1717_CR42) 2007; 40 Y Yamauchi (1717_CR33) 2023; 9 1717_CR50 1717_CR51 1717_CR52 1717_CR10 1717_CR54 1717_CR11 1717_CR55 1717_CR12 1717_CR56 1717_CR13 1717_CR57 1717_CR58 1717_CR15 1717_CR17 1717_CR18 R Gal (1717_CR40) 2006; 25 R Osada (1717_CR36) 2002; 21 G Flitton (1717_CR21) 2015; 48 M Novotni (1717_CR38) 2004; 36 D Velayudhan (1717_CR22) 2022; 55 Z Zhu (1717_CR44) 2016; 204 Y Nagai (1717_CR23) 2019; 107 1717_CR60 1717_CR61 1717_CR62 L Yi (1717_CR6) 2016; 35 1717_CR63 1717_CR66 1717_CR67 1717_CR24 1717_CR25 1717_CR26 H Yang (1717_CR53) 2020; 37 M Werning (1717_CR1) 2012 1717_CR27 1717_CR28 1717_CR29 1717_CR2 1717_CR5 1717_CR4 1717_CR7 1717_CR9 1717_CR8 A Wolny (1717_CR14) 2020; 9 S Wolf (1717_CR16) 2020; 43 S Lloyd (1717_CR64) 1982; 28 W Pullan (1717_CR69) 2006; 12 1717_CR70 PJ Besl (1717_CR65) 1992; 1611 1717_CR71 1717_CR72 1717_CR73 1717_CR30 1717_CR74 1717_CR75 1717_CR32 1717_CR76 1717_CR34 GT Flitton (1717_CR19) 2010; 1 1717_CR37 G Flitton (1717_CR20) 2013; 46 C Zhuang (1717_CR35) 2021; 68 PR Östergård (1717_CR68) 2002; 120 A Ferreira (1717_CR31) 2010; 89 S Chopra (1717_CR59) 1993; 59
References_xml	– ident: 1717_CR63 doi: 10.1201/9781482277234-12 – volume: 107 start-page: 23 year: 2019 ident: 1717_CR23 publication-title: Comput. Aided Des. doi: 10.1016/j.cad.2018.09.002 – ident: 1717_CR17 doi: 10.1109/CVPR52688.2022.01135 – ident: 1717_CR67 doi: 10.1137/1.9781611975499.12 – volume: 46 start-page: 2420 issue: 9 year: 2013 ident: 1717_CR20 publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2013.02.008 – ident: 1717_CR61 doi: 10.1007/978-3-642-23094-3_3 – ident: 1717_CR10 doi: 10.1007/978-3-030-58452-8_13 – volume: 4 start-page: 629 issue: 5 year: 2007 ident: 1717_CR41 publication-title: Comput. Aided Des. Appl. doi: 10.1080/16864360.2007.10738497 – ident: 1717_CR74 doi: 10.1109/CVPR.2019.00963 – ident: 1717_CR45 doi: 10.1109/ICCV.2017.26 – volume: 43 start-page: 3724 issue: 10 year: 2020 ident: 1717_CR16 publication-title: IEEE Trans. Pattern Analy. Machine Intell. doi: 10.1109/TPAMI.2020.2980827 – volume: 37 start-page: 314 issue: 2 year: 2020 ident: 1717_CR53 publication-title: IEEE Trans. Rob. doi: 10.1109/TRO.2020.3033695 – ident: 1717_CR18 – volume: 28 start-page: 129 issue: 2 year: 1982 ident: 1717_CR64 publication-title: IEEE Trans. Inf. Theory doi: 10.1109/TIT.1982.1056489 – ident: 1717_CR9 doi: 10.1109/CVPR52688.2022.00823 – ident: 1717_CR34 doi: 10.23919/MVA.2017.7986888 – ident: 1717_CR37 – ident: 1717_CR54 doi: 10.1145/2739480.2754667 – ident: 1717_CR4 doi: 10.1109/CVPR.2012.6248074 – ident: 1717_CR56 – ident: 1717_CR7 doi: 10.1109/CVPR.2018.00472 – volume: 9 start-page: 319 issue: 2 year: 2023 ident: 1717_CR33 publication-title: Comput. Visual Media doi: 10.1007/s41095-022-0296-2 – volume: 36 start-page: 1047 issue: 11 year: 2004 ident: 1717_CR38 publication-title: Comput. Aided Des. doi: 10.1016/j.cad.2004.01.005 – volume: 48 start-page: 2489 issue: 8 year: 2015 ident: 1717_CR21 publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2015.02.006 – volume: 12 start-page: 303 year: 2006 ident: 1717_CR69 publication-title: J. Comb. Optim. doi: 10.1007/s10878-006-9635-y – ident: 1717_CR62 doi: 10.1109/CVPR.2013.175 – ident: 1717_CR55 doi: 10.1145/3355089.3356504 – volume-title: The oxford handbook of compositionality year: 2012 ident: 1717_CR1 – ident: 1717_CR13 doi: 10.1109/3DV.2016.79 – volume: 21 start-page: 807 issue: 4 year: 2002 ident: 1717_CR36 publication-title: ACM Trans. Graphics (TOG) doi: 10.1145/571647.571648 – ident: 1717_CR49 doi: 10.1109/SMI.2008.4547955 – ident: 1717_CR50 doi: 10.1007/978-3-642-15561-1_11 – volume: 120 start-page: 197 issue: 1–3 year: 2002 ident: 1717_CR68 publication-title: Discret. Appl. Math. doi: 10.1016/S0166-218X(01)00290-6 – volume: 35 start-page: 1 issue: 6 year: 2016 ident: 1717_CR6 publication-title: ACM Trans. Graphics (ToG) doi: 10.1145/2980179.2980238 – ident: 1717_CR15 – ident: 1717_CR11 doi: 10.1109/WACV48630.2021.00038 – volume: 204 start-page: 41 year: 2016 ident: 1717_CR44 publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.08.127 – ident: 1717_CR12 doi: 10.1007/978-3-319-24574-4_28 – volume: 40 start-page: 283 issue: 1 year: 2007 ident: 1717_CR42 publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2006.04.034 – ident: 1717_CR52 doi: 10.1007/978-3-319-46475-6_47 – ident: 1717_CR2 – ident: 1717_CR8 doi: 10.1109/CVPR42600.2020.00178 – ident: 1717_CR29 doi: 10.1109/CVPR.2018.00208 – volume: 60 start-page: 91 year: 2004 ident: 1717_CR39 publication-title: Int. J. Comput. Vision doi: 10.1023/B:VISI.0000029664.99615.94 – ident: 1717_CR73 – ident: 1717_CR25 – volume: 89 start-page: 327 year: 2010 ident: 1717_CR31 publication-title: Int. J. Comput. Vision doi: 10.1007/s11263-009-0257-6 – ident: 1717_CR57 doi: 10.1007/978-3-031-19815-1_6 – ident: 1717_CR70 doi: 10.1007/978-3-030-89543-3_51 – ident: 1717_CR75 doi: 10.1109/CVPR52729.2023.00827 – volume: 1 start-page: 1 year: 2010 ident: 1717_CR19 publication-title: BMVC – ident: 1717_CR26 doi: 10.12981/motif.356 – ident: 1717_CR46 doi: 10.1109/ICCV.2019.00905 – ident: 1717_CR43 doi: 10.1109/ROBOT.2009.5152473 – volume: 63 start-page: 655 issue: 2 year: 2014 ident: 1717_CR3 publication-title: CIRP Ann. doi: 10.1016/j.cirp.2014.05.011 – ident: 1717_CR58 – ident: 1717_CR66 doi: 10.15607/RSS.2009.V.021 – volume: 25 start-page: 130 issue: 1 year: 2006 ident: 1717_CR40 publication-title: ACM Trans. Graphics (TOG) doi: 10.1145/1122501.1122507 – volume: 9 start-page: 57613 year: 2020 ident: 1717_CR14 publication-title: Elife doi: 10.7554/eLife.57613 – ident: 1717_CR76 doi: 10.1109/CVPR.2019.00656 – volume: 55 start-page: 1 issue: 8 year: 2022 ident: 1717_CR22 publication-title: ACM Comput. Surveys doi: 10.1145/3549932 – volume: 68 year: 2021 ident: 1717_CR35 publication-title: Robotics Comput. Integ. Manufact. doi: 10.1016/j.rcim.2020.102086 – volume: 59 start-page: 87 issue: 1–3 year: 1993 ident: 1717_CR59 publication-title: Mathe. Program. doi: 10.1007/BF01581239 – volume: 1611 start-page: 586 year: 1992 ident: 1717_CR65 publication-title: Sensor Fusion IV Control Paradigms Data Struct. doi: 10.1117/12.57955 – ident: 1717_CR24 – ident: 1717_CR48 – ident: 1717_CR51 doi: 10.1007/978-3-642-25382-9_2 – ident: 1717_CR28 doi: 10.1109/SMI.2004.1314502 – volume: 69 year: 2021 ident: 1717_CR47 publication-title: Displays doi: 10.1016/j.displa.2021.102053 – ident: 1717_CR60 doi: 10.1109/ICCV.2011.6126550 – ident: 1717_CR30 – ident: 1717_CR5 doi: 10.1109/CVPR46437.2021.00738 – ident: 1717_CR27 doi: 10.1109/CVPR.2010.5540108 – ident: 1717_CR71 doi: 10.1109/CVPR52688.2022.01539 – ident: 1717_CR32 doi: 10.1109/ICARSC55462.2022.9784795 – ident: 1717_CR72
SSID	ssj0004774
Score	2.4119475
Snippet	Many technical products are assemblies formed from smaller, versatile building blocks. Deconstructing such assemblies is an industrially important problem and...
SourceID	proquest crossref springer
SourceType	Aggregation Database Index Database Publisher
StartPage	8
SubjectTerms	Algorithms Annotations Assemblies Automation Aviation Communications Engineering Computed tomography Computer Science Datasets High resolution Image Processing and Computer Vision Localization Machine learning Medical imaging Networks Pattern Recognition Quality control Segments
Title	Deconstruct to reconstruct: an automated pipeline for parsing complex CT assemblies
URI	https://link.springer.com/article/10.1007/s00138-025-01717-5 https://www.proquest.com/docview/3274111807
Volume	37
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 1432-1769 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004774 issn: 0932-8092 databaseCode: RSV dateStart: 19970101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwED5BYYCBRwFRKMgDG1jKy3HChgoVU4VoQd0iO3akDqRRUxA_n7OTNIBggDGO5UR3tu87n-87gAtHod1SnkszlUoaCMapVDymKmBuhu6YdERgi03w0SiaTuOHOimsbG67NyFJu1Ovkt1sUI2a8quG44VTtg4baO4iU7DhcfzcZkPyinsZkQnuv7FXp8r8PMZXc9RizG9hUWtthrv_-8892KnRJbmppsM-rOm8C7s10iT1Oi6xqSnm0LR1YfsTM-EBjG-No1yRy5LlnCzax2siciJel3PEujhoMStMSrsmiH5JIezZA7EX1fU7GUwIgnP9IvH75SE8De8mg3ta11-gKaI-Rk1ReZeHacCl8OLUybwYnSfpaa4E90WmGRPo1KZMmdToIBNRFgZS8jjiqWLa8Y-gk89zfQxEe47UkSey0E-xiyPDzI99FaF76WrfD3tw2aghKSqajWRFqGwFmqBAEyvQhPWg32gqqZdcmfiGiMcQ2vEeXDWaaV__PtrJ37qfwpaHjmt1DNOHDopen8Fm-raclYtzOxU_APpt16A
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1NT8MwDLVgIAEHBgPE-MyBG0Tq2qZpuaHBNMSYEBtotyppUmkHtmkdiJ-Pk7YbIDjAsWmUVnYSP8fxM8CZo9BuKbdBU5VI6gvGqVQ8ospnjRTdMekI3xab4N1uOBhED0VSWFbedi9Dknannie72aAaNeVXDccLp2wZVny0WIYx_7H3vMiG5Dn3MiIT3H8jt0iV-XmMr-ZogTG_hUWttWlV__efW7BZoEtylU-HbVjSoxpUC6RJinWcYVNZzKFsq8HGJ2bCHehdG0c5J5clszGZLh4viRgR8TobI9bFQSfDiUlp1wTRL5kIe_ZA7EV1_U6afYLgXL9I_H62C0-tm36zTYv6CzRB1MeoKSrf4EHicyncKHFSN0LnSbqaK8E9kWrGBDq1CVMmNdpPRZgGvpQ8CnmimHa8PaiMxiO9D0S7jtShK9LAS7CLI4PUizwVonvZ0J4X1OG8VEM8yWk24jmhshVojAKNrUBjVoejUlNxseSy2DNEPIbQjtfhotTM4vXvox38rfsprLX79524c9u9O4R1F53Y_EjmCCqoBn0Mq8nbbJhNT-y0_AAfNdqE
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1dS8MwFL34heiDH1NxOjUPvmlY1zZN65uoQ1HGwA_2VpImgT3YFTfFn-9N2rop-iA-tg1pyU2ac5KccwGOPYXzlvI71KhM0lAwTqXiCVUh6xikY9IToUs2wXu9eDBI-jMqfnfavd6SLDUN1qUpn7QLZdqfwje3wUZtKlbr98Ipm4fF0B6kt3z9_mmqjOSlDzOiFPwXJ34lm_m5jq9T0xRvftsidTNPd_3_37wBaxXqJOdlN9mEOZ03YL1CoKQa32O8VSd5qO81YHXGsXAL7i8tgS5NZ8lkRF6ml2dE5ES8TkaIgbHSYlhYqbsmiIpJIdyaBHEH2PU7uXggCNr1s8T3j7fhsXv1cHFNq7wMNEM0yKhNNt_hURZyKfwk84yfIKmSvuZK8EAYzZhAspsxZSXToRGxiUIpeRLzTDHtBTuwkI9yvQtE-57UsS9MFGRYxJORCZJAxUg7OzoIoiac1CFJi9J-I_00WnYNmmKDpq5BU9aEVh21tBqK4zSwBj3W6I434bSO0vTx77Xt_a34ESz3L7vp3U3vdh9WfOS25UpNCxYwCvoAlrK3yXD8cuh66Af-LeNo
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=Deconstruct+to+reconstruct%3A+an+automated+pipeline+for+parsing+complex+CT+assemblies&rft.jtitle=Machine+vision+and+applications&rft.au=Lippmann%2C+Peter&rft.au=Remme%2C+Roman&rft.au=Hamprecht%2C+Fred+A.&rft.date=2026-01-01&rft.pub=Springer+Berlin+Heidelberg&rft.issn=0932-8092&rft.eissn=1432-1769&rft.volume=37&rft.issue=1&rft_id=info:doi/10.1007%2Fs00138-025-01717-5&rft.externalDocID=10_1007_s00138_025_01717_5
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0932-8092&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0932-8092&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0932-8092&client=summon