Component-aware generative autoencoder for structure hybrid and shape completion
Assembling components of man-made objects to create new structures or complete 3D shapes is a popular approach in 3D modeling techniques. Recently, leveraging deep neural networks for assembly-based 3D modeling has been widely studied. However, exploring new component combinations even across differ...
Gespeichert in:
| Veröffentlicht in: | Graphical models Jg. 129; S. 101185 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Elsevier Inc
01.10.2023
Elsevier |
| Schlagworte: | |
| ISSN: | 1524-0703, 1524-0711 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Assembling components of man-made objects to create new structures or complete 3D shapes is a popular approach in 3D modeling techniques. Recently, leveraging deep neural networks for assembly-based 3D modeling has been widely studied. However, exploring new component combinations even across different categories is still challenging for most of the deep-learning-based 3D modeling methods. In this paper, we propose a novel generative autoencoder that tackles the component combinations for 3D modeling of man-made objects. We use the segmented input objects to create component volumes that have redundant components and random configurations. By using the input objects and the associated component volumes to train the autoencoder, we can obtain an object volume consisting of components with proper quality and structure as the network output. Such a generative autoencoder can be applied to either multiple object categories for structure hybrid or a single object category for shape completion. We conduct a series of evaluations and experimental results to demonstrate the usability and practicability of our method.
[Display omitted] |
|---|---|
| AbstractList | Assembling components of man-made objects to create new structures or complete 3D shapes is a popular approach in 3D modeling techniques. Recently, leveraging deep neural networks for assembly-based 3D modeling has been widely studied. However, exploring new component combinations even across different categories is still challenging for most of the deep-learning-based 3D modeling methods. In this paper, we propose a novel generative autoencoder that tackles the component combinations for 3D modeling of man-made objects. We use the segmented input objects to create component volumes that have redundant components and random configurations. By using the input objects and the associated component volumes to train the autoencoder, we can obtain an object volume consisting of components with proper quality and structure as the network output. Such a generative autoencoder can be applied to either multiple object categories for structure hybrid or a single object category for shape completion. We conduct a series of evaluations and experimental results to demonstrate the usability and practicability of our method.
[Display omitted] Assembling components of man-made objects to create new structures or complete 3D shapes is a popular approach in 3D modeling techniques. Recently, leveraging deep neural networks for assembly-based 3D modeling has been widely studied. However, exploring new component combinations even across different categories is still challenging for most of the deep-learning-based 3D modeling methods. In this paper, we propose a novel generative autoencoder that tackles the component combinations for 3D modeling of man-made objects. We use the segmented input objects to create component volumes that have redundant components and random configurations. By using the input objects and the associated component volumes to train the autoencoder, we can obtain an object volume consisting of components with proper quality and structure as the network output. Such a generative autoencoder can be applied to either multiple object categories for structure hybrid or a single object category for shape completion. We conduct a series of evaluations and experimental results to demonstrate the usability and practicability of our method. |
| ArticleNumber | 101185 |
| Author | Liu, Yang Fu, Qiang Li, Xueming Zhang, Fan |
| Author_xml | – sequence: 1 givenname: Fan orcidid: 0000-0003-3486-6040 surname: Zhang fullname: Zhang, Fan email: zhangfan.kanv@gmail.com – sequence: 2 givenname: Qiang orcidid: 0000-0002-8944-8981 surname: Fu fullname: Fu, Qiang email: fu.john.qiang@gmail.com – sequence: 3 givenname: Yang orcidid: 0000-0001-9814-638X surname: Liu fullname: Liu, Yang email: yang.liu@bupt.edu.cn – sequence: 4 givenname: Xueming orcidid: 0000-0003-1058-2799 surname: Li fullname: Li, Xueming email: lixm@bupt.edu.cn |
| BookMark | eNp9kMtqYzEMhk3pwPQyLzCr8wIntezYx4HZDGF6gUK7aNdGtuXUITkOPk6Hvn2dpnTZlYTQ_yF95-x0zCMx9hv4DDjoq_Vstc1hJriQhwEYdcLOQIl5zweA06-ey5_sfJrWvO2ouThjj8u83TXWWHv8j4W6FY1UsKZX6nBfM40-BypdzKWbatn7um9LL2-upNDhGLrpBXfU-UbZUE15vGQ_Im4m-vVZL9jz9b-n5W1__3Bzt_x733upofYgdATnotfSLwYzF2EwXEoRKAJ67hwgGYoBolBm0MoNBiM3Ug0Rohm8vGB3R27IuLa7krZY3mzGZD8Guawslpr8hqxR6CBIHUCpOTiN6KKDhdZOk-eLRWOJI8uXPE2F4hcPuD34tWt78GsPfu3Rbwv9OYaoffmaqNjJp6aLQirkazsjfRd_B7WPhvk |
| Cites_doi | 10.1145/2185520.2185550 10.1145/2185520.2185551 10.1145/2185520.2185553 10.1145/3072959.3073637 10.1109/CVPR.2018.00745 10.1145/3272127.3275008 10.1145/1882261.1866206 10.1109/CVPR52688.2022.00040 10.1145/1778765.1778841 10.1016/j.cag.2015.06.009 10.1109/TPAMI.2009.161 10.1109/ICCV.2019.00885 10.1145/2461912.2461924 10.1145/2366145.2366199 10.1145/3130800.3130821 10.1145/2010324.1964930 10.1145/1882261.1866205 10.1109/TVCG.2020.3029759 10.1109/CVPR.2017.603 10.1145/2601097.2601185 10.1145/2461912.2461933 10.1145/2601097.2601102 10.1109/TVCG.2017.2739159 10.1145/1015706.1015775 10.1145/2010324.1964928 10.1016/j.gmod.2016.01.002 10.1609/aaai.v34i07.6798 |
| ContentType | Journal Article |
| Copyright | 2023 The Authors |
| Copyright_xml | – notice: 2023 The Authors |
| DBID | 6I. AAFTH AAYXX CITATION DOA |
| DOI | 10.1016/j.gmod.2023.101185 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1524-0711 |
| ExternalDocumentID | oai_doaj_org_article_85ab1d36d15541b6aabfb1966b6ec099 10_1016_j_gmod_2023_101185 S1524070323000152 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 29I 4.4 457 4G. 5GY 5VS 6I. 6TJ 7-5 71M 8P~ AACTN AAEDT AAEDW AAFTH AAFWJ AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABAOU ABBOA ABFNM ABMAC ABXDB ABYKQ ACAZW ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADFGL ADGUI ADJOM ADMUD AEBSH AEKER AENEX AEXQZ AFKWA AFPKN AFTJW AGHFR AGUBO AGYEJ AHZHX AIALX AIEXJ AIGVJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BKOJK BLXMC CAG COF CS3 DM4 DU5 EBS EFBJH EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ GROUPED_DOAJ HF~ HVGLF HZ~ IHE J1W KOM LG5 M41 MHUIS MO0 N9A O-L O9- OAUVE OZT P-8 P-9 PC. Q38 R2- RIG ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SSV SSW SSZ T5K TN5 UHS XPP ZMT ZU3 ~02 ~G- 9DU AATTM AAXKI AAYWO AAYXX ABJNI ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO ADVLN AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c361t-126f1bbfc63c97842d780332def1ac0bb1ae8efd1f258765b78af08357f1f87c3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001046647500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1524-0703 |
| IngestDate | Fri Oct 03 12:52:50 EDT 2025 Sat Nov 29 07:01:33 EST 2025 Fri Feb 23 02:37:56 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Generative autoencoder Structure hybrid 3D modeling Shape completion |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c361t-126f1bbfc63c97842d780332def1ac0bb1ae8efd1f258765b78af08357f1f87c3 |
| ORCID | 0000-0003-3486-6040 0000-0003-1058-2799 0000-0001-9814-638X 0000-0002-8944-8981 |
| OpenAccessLink | https://doaj.org/article/85ab1d36d15541b6aabfb1966b6ec099 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_85ab1d36d15541b6aabfb1966b6ec099 crossref_primary_10_1016_j_gmod_2023_101185 elsevier_sciencedirect_doi_10_1016_j_gmod_2023_101185 |
| PublicationCentury | 2000 |
| PublicationDate | October 2023 2023-10-00 2023-10-01 |
| PublicationDateYYYYMMDD | 2023-10-01 |
| PublicationDate_xml | – month: 10 year: 2023 text: October 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Graphical models |
| PublicationYear | 2023 |
| Publisher | Elsevier Inc Elsevier |
| Publisher_xml | – name: Elsevier Inc – name: Elsevier |
| References | Xu, Zhang, Cohen-Or, Chen (b32) 2012; 31 Bokeloh, Wand, Seidel (b35) 2010; 29 Fish, Averkiou, Van Kaick, Sorkine-Hornung, Cohen-Or, Mitra (b14) 2014; 33 Zhu, Xu, Chaudhuri, Yi, Zhang (b4) 2018; 37 Van Kaick, Tagliasacchi, Sidi, Zhang, Cohen-Or, Wolf, Hamarneh (b25) 2011 Su, Chen, Fu, Fu (b9) 2016; 54 Funkhouser, Kazhdan, Shilane, Min, Kiefer, Tal, Rusinkiewicz, Dobkin (b10) 2004; 23 Mo, Guerrero, Yi, Su, Wonka, Mitra, Guibas (b16) 2019 Kreavoy, Julius, Sheffer (b21) 2007 Xie, Yao, Sun, Zhou, Zhang (b40) 2019 Yin, Chen, Chaudhuri, Fisher, Kim, Zhang (b17) 2020 Wang, Guerrero, Kim, Chaudhuri, Sung, Ritchie (b18) 2022 P. Mittal, Y.-C. Cheng, M. Singh, S. Tulsiani, AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 306–315. J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132–7141. J. Li, C. Niu, K. Xu, Learning Part Generation and Assembly for Structure-Aware Shape Synthesis, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2020, pp. 11362–11369. Fu, Chen, Su, Fu (b34) 2016; 85 Fu, Chen, Su, Fu (b8) 2017; 23 Fu, Chen, Su, Li, Fu (b15) 2016 Jain, Thormählen, Ritschel, Seidel (b30) 2012 Wang, Guerrero, Kim, Chaudhuri, Sung, Ritchie (b7) 2021 Kalogerakis, Chaudhuri, Koller, Koltun (b31) 2012; 31 Hertz, Perel, Giryes, Sorkine-Hornung, Cohen-Or (b23) 2022 Chaudhuri, Koltun (b12) 2010; 29 Jin, Fu, Deng (b38) 2020 Furukawa, Ponce (b2) 2009; 32 Chaudhuri, Kalogerakis, Guibas, Koltun (b20) 2011; 30 Zheng, Cohen-Or, Averkiou, Mitra (b28) 2014 Lee, Funkhouser (b11) 2008 Xu, Li, Zhang, Cohen-Or, Xiong, Cheng (b37) 2010; 29 Van Kaick, Xu, Zhang, Wang, Sun, Shamir, Cohen-Or (b27) 2013; 32 Kim, Li, Mitra, Chaudhuri, DiVerdi, Funkhouser (b29) 2013; 32 Chang, Funkhouser, Guibas, Hanrahan, Huang, Li, Savarese, Savva, Song, Su (b41) 2015 Zheng, Cohen-Or, Mitra (b33) 2013 Shen, Fu, Chen, Hu (b42) 2012; 31 N. Schor, O. Katzir, H. Zhang, D. Cohen-Or, CompoNet: Learning to generate the unseen by part synthesis and composition, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 8759–8768. D. Tome, C. Russell, L. Agapito, Lifting from the deep: Convolutional 3d pose estimation from a single image, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2500–2509. Guan, Liu, Liu, Yin, Hu, van Kaick, Zhang, Yumer, Carr, Mech, Zhang (b39) 2022; 28 Ovsjanikov, Li, Guibas, Mitra (b13) 2011; 30 Alhashim, Li, Xu, Cao, Ma, Zhang (b36) 2014; 33 Wang, Xu, Li, Zhang, Shamir, Liu, Cheng, Xiong (b26) 2011 J. Wu, C. Zhang, T. Xue, W.T. Freeman, J.B. Tenenbaum, Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling, in: Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS ’16, Red Hook, NY, USA, 2016, pp. 82–90. Li, Xu, Chaudhuri, Yumer, Zhang, Guibas (b6) 2017; 36 Sung, Su, Kim, Chaudhuri, Guibas (b22) 2017; 36 Kim, Li, Mitra, DiVerdi, Funkhouser (b24) 2012; 31 Li (10.1016/j.gmod.2023.101185_b6) 2017; 36 Sung (10.1016/j.gmod.2023.101185_b22) 2017; 36 Jin (10.1016/j.gmod.2023.101185_b38) 2020 Wang (10.1016/j.gmod.2023.101185_b26) 2011 Fu (10.1016/j.gmod.2023.101185_b15) 2016 10.1016/j.gmod.2023.101185_b44 10.1016/j.gmod.2023.101185_b43 Zheng (10.1016/j.gmod.2023.101185_b28) 2014 Xu (10.1016/j.gmod.2023.101185_b32) 2012; 31 Su (10.1016/j.gmod.2023.101185_b9) 2016; 54 Kalogerakis (10.1016/j.gmod.2023.101185_b31) 2012; 31 Furukawa (10.1016/j.gmod.2023.101185_b2) 2009; 32 10.1016/j.gmod.2023.101185_b5 10.1016/j.gmod.2023.101185_b19 10.1016/j.gmod.2023.101185_b3 Funkhouser (10.1016/j.gmod.2023.101185_b10) 2004; 23 10.1016/j.gmod.2023.101185_b1 Yin (10.1016/j.gmod.2023.101185_b17) 2020 Chang (10.1016/j.gmod.2023.101185_b41) 2015 Wang (10.1016/j.gmod.2023.101185_b18) 2022 Kim (10.1016/j.gmod.2023.101185_b29) 2013; 32 Kim (10.1016/j.gmod.2023.101185_b24) 2012; 31 Van Kaick (10.1016/j.gmod.2023.101185_b27) 2013; 32 Xie (10.1016/j.gmod.2023.101185_b40) 2019 Hertz (10.1016/j.gmod.2023.101185_b23) 2022 Shen (10.1016/j.gmod.2023.101185_b42) 2012; 31 Zheng (10.1016/j.gmod.2023.101185_b33) 2013 Mo (10.1016/j.gmod.2023.101185_b16) 2019 Alhashim (10.1016/j.gmod.2023.101185_b36) 2014; 33 Zhu (10.1016/j.gmod.2023.101185_b4) 2018; 37 Chaudhuri (10.1016/j.gmod.2023.101185_b12) 2010; 29 Fish (10.1016/j.gmod.2023.101185_b14) 2014; 33 Jain (10.1016/j.gmod.2023.101185_b30) 2012 Lee (10.1016/j.gmod.2023.101185_b11) 2008 Chaudhuri (10.1016/j.gmod.2023.101185_b20) 2011; 30 Kreavoy (10.1016/j.gmod.2023.101185_b21) 2007 Fu (10.1016/j.gmod.2023.101185_b34) 2016; 85 Xu (10.1016/j.gmod.2023.101185_b37) 2010; 29 Bokeloh (10.1016/j.gmod.2023.101185_b35) 2010; 29 Guan (10.1016/j.gmod.2023.101185_b39) 2022; 28 Van Kaick (10.1016/j.gmod.2023.101185_b25) 2011 Wang (10.1016/j.gmod.2023.101185_b7) 2021 Fu (10.1016/j.gmod.2023.101185_b8) 2017; 23 Ovsjanikov (10.1016/j.gmod.2023.101185_b13) 2011; 30 |
| References_xml | – reference: N. Schor, O. Katzir, H. Zhang, D. Cohen-Or, CompoNet: Learning to generate the unseen by part synthesis and composition, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 8759–8768. – volume: 32 start-page: 70:1 year: 2013 end-page: 70:12 ident: b29 article-title: Learning part-based templates from large collections of 3D shapes publication-title: ACM Trans. Graph. – volume: 85 start-page: 1 year: 2016 end-page: 10 ident: b34 article-title: Natural lines inspired 3D shape re-design publication-title: Graph. Models – reference: J. Li, C. Niu, K. Xu, Learning Part Generation and Assembly for Structure-Aware Shape Synthesis, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2020, pp. 11362–11369. – start-page: 9:1 year: 2020 end-page: 9:10 ident: b38 article-title: Contour-based 3D modeling through joint embedding of shapes and contours publication-title: Symposium on Interactive 3D Graphics and Games – start-page: 61 year: 2020 end-page: 70 ident: b17 article-title: Coalesce: Component assembly by learning to synthesize connections publication-title: 2020 International Conference on 3D Vision – volume: 23 start-page: 2574 year: 2017 end-page: 2585 ident: b8 article-title: Pose-inspired shape synthesis and functional hybrid publication-title: IEEE Trans. Vis. Comput. Graphics – start-page: 129 year: 2007 end-page: 138 ident: b21 article-title: Model composition from interchangeable components publication-title: 15th Pacific Conference on Computer Graphics and Applications – volume: 29 start-page: 104:1 year: 2010 end-page: 104:10 ident: b35 article-title: A connection between partial symmetry and inverse procedural modeling publication-title: ACM Trans. Graph. – volume: 31 start-page: 180:1 year: 2012 end-page: 180:11 ident: b42 article-title: Structure recovery by part assembly publication-title: ACM Trans. Graph. – start-page: 287 year: 2011 end-page: 296 ident: b26 article-title: Symmetry hierarchy of man-made objects publication-title: Computer Graphics Forum, Vol. 30, No. 2 – start-page: 27 year: 2016 end-page: 36 ident: b15 article-title: Structure-adaptive shape editing for man-made objects publication-title: Computer Graphics Forum, Vol. 35, No. 2 – volume: 29 start-page: 183:1 year: 2010 end-page: 183:10 ident: b12 article-title: Data-driven suggestions for creativity support in 3D modeling publication-title: ACM Trans. Graph. – start-page: 2690 year: 2019 end-page: 2698 ident: b40 article-title: Pix2Vox: Context-aware 3D reconstruction from single and multi-view images publication-title: 2019 IEEE/CVF International Conference on Computer Vision – volume: 30 start-page: 35:1 year: 2011 end-page: 35:10 ident: b20 article-title: Probabilistic reasoning for assembly-based 3D modeling publication-title: ACM Trans. Graph. – volume: 33 start-page: 34:1 year: 2014 end-page: 34:11 ident: b14 article-title: Meta-representation of shape families publication-title: ACM Trans. Graph. – volume: 32 start-page: 1362 year: 2009 end-page: 1376 ident: b2 article-title: Accurate, dense, and robust multiview stereopsis publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 37 start-page: 211:1 year: 2018 end-page: 211:14 ident: b4 article-title: SCORES: Shape composition with recursive substructure priors publication-title: ACM Trans. Graph. – volume: 32 start-page: 69:1 year: 2013 end-page: 69:10 ident: b27 article-title: Co-hierarchical analysis of shape structures publication-title: ACM Trans. Graph. – reference: J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132–7141. – volume: 31 start-page: 54:1 year: 2012 end-page: 54:11 ident: b24 article-title: Exploring collections of 3d models using fuzzy correspondences publication-title: ACM Trans. Graph. – volume: 36 start-page: 1 year: 2017 end-page: 12 ident: b22 article-title: ComplementMe: Weakly-supervised component suggestions for 3D modeling publication-title: ACM Trans. Graph. – reference: P. Mittal, Y.-C. Cheng, M. Singh, S. Tulsiani, AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 306–315. – year: 2019 ident: b16 article-title: Structurenet: Hierarchical graph networks for 3d shape generation – year: 2022 ident: b23 article-title: SPAGHETTI: Editing implicit shapes through part aware generation – volume: 54 start-page: 145 year: 2016 end-page: 153 ident: b9 article-title: Cross-class 3D object synthesis guided by reference examples publication-title: Comput. Graph. – volume: 30 start-page: 33:1 year: 2011 end-page: 33:10 ident: b13 article-title: Exploration of continuous variability in collections of 3d shapes publication-title: ACM Trans. Graph. – start-page: 631 year: 2012 end-page: 640 ident: b30 article-title: Exploring shape variations by 3d-model decomposition and part-based recombination publication-title: Computer Graphics Forum, Vol. 31, No. 2pt3 – start-page: 97 year: 2008 end-page: 104 ident: b11 article-title: Sketch-based search and composition of 3D models publication-title: SBIM – start-page: 195 year: 2013 end-page: 204 ident: b33 article-title: Smart variations: Functional substructures for part compatibility publication-title: Computer Graphics Forum, Vol. 32, No. 2pt2 – volume: 23 start-page: 652 year: 2004 end-page: 663 ident: b10 article-title: Modeling by example publication-title: ACM Trans. Graph. – volume: 28 start-page: 1758 year: 2022 end-page: 1772 ident: b39 article-title: FAME: 3D shape generation via functionality-aware model evolution publication-title: IEEE Trans. Vis. Comput. Graphics – year: 2015 ident: b41 article-title: Shapenet: An information-rich 3d model repository – volume: 33 start-page: 158:1 year: 2014 end-page: 158:10 ident: b36 article-title: Topology-varying 3D shape creation via structural blending publication-title: ACM Trans. Graph. – volume: 36 start-page: 52:1 year: 2017 end-page: 52:14 ident: b6 article-title: Grass: Generative recursive autoencoders for shape structures publication-title: ACM Trans. Graph. – start-page: 1 year: 2021 end-page: 19 ident: b7 article-title: The shape part slot machine: Contact-based reasoning for generating 3D shapes from parts – volume: 31 start-page: 55:1 year: 2012 end-page: 55:11 ident: b31 article-title: A probabilistic model for component-based shape synthesis publication-title: ACM Trans. Graph. (TOG) – volume: 31 start-page: 57:1 year: 2012 end-page: 57:10 ident: b32 article-title: Fit and diverse: Set evolution for inspiring 3d shape galleries publication-title: ACM Trans. Graph. – start-page: 610 year: 2022 end-page: 626 ident: b18 article-title: The shape part slot machine: Contact-based reasoning for generating 3D shapes from parts publication-title: European Conference on Computer Vision – start-page: 553 year: 2011 end-page: 562 ident: b25 article-title: Prior knowledge for part correspondence publication-title: Computer Graphics Forum, Vol. 30, No. 2 – reference: D. Tome, C. Russell, L. Agapito, Lifting from the deep: Convolutional 3d pose estimation from a single image, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2500–2509. – volume: 29 start-page: 184:1 year: 2010 end-page: 184:10 ident: b37 article-title: Style-content separation by anisotropic part scales publication-title: ACM Trans. Graph. – reference: J. Wu, C. Zhang, T. Xue, W.T. Freeman, J.B. Tenenbaum, Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling, in: Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS ’16, Red Hook, NY, USA, 2016, pp. 82–90. – start-page: 115 year: 2014 end-page: 124 ident: b28 article-title: Recurring part arrangements in shape collections publication-title: Computer Graphics Forum, Vol. 33, No. 2 – year: 2022 ident: 10.1016/j.gmod.2023.101185_b23 – volume: 31 start-page: 54:1 issue: 4 year: 2012 ident: 10.1016/j.gmod.2023.101185_b24 article-title: Exploring collections of 3d models using fuzzy correspondences publication-title: ACM Trans. Graph. doi: 10.1145/2185520.2185550 – volume: 31 start-page: 55:1 issue: 4 year: 2012 ident: 10.1016/j.gmod.2023.101185_b31 article-title: A probabilistic model for component-based shape synthesis publication-title: ACM Trans. Graph. (TOG) doi: 10.1145/2185520.2185551 – volume: 31 start-page: 57:1 issue: 4 year: 2012 ident: 10.1016/j.gmod.2023.101185_b32 article-title: Fit and diverse: Set evolution for inspiring 3d shape galleries publication-title: ACM Trans. Graph. doi: 10.1145/2185520.2185553 – volume: 36 start-page: 52:1 issue: 4 year: 2017 ident: 10.1016/j.gmod.2023.101185_b6 article-title: Grass: Generative recursive autoencoders for shape structures publication-title: ACM Trans. Graph. doi: 10.1145/3072959.3073637 – ident: 10.1016/j.gmod.2023.101185_b43 doi: 10.1109/CVPR.2018.00745 – volume: 37 start-page: 211:1 issue: 6 year: 2018 ident: 10.1016/j.gmod.2023.101185_b4 article-title: SCORES: Shape composition with recursive substructure priors publication-title: ACM Trans. Graph. doi: 10.1145/3272127.3275008 – volume: 29 start-page: 184:1 issue: 6 year: 2010 ident: 10.1016/j.gmod.2023.101185_b37 article-title: Style-content separation by anisotropic part scales publication-title: ACM Trans. Graph. doi: 10.1145/1882261.1866206 – ident: 10.1016/j.gmod.2023.101185_b44 doi: 10.1109/CVPR52688.2022.00040 – volume: 29 start-page: 104:1 issue: 4 year: 2010 ident: 10.1016/j.gmod.2023.101185_b35 article-title: A connection between partial symmetry and inverse procedural modeling publication-title: ACM Trans. Graph. doi: 10.1145/1778765.1778841 – volume: 54 start-page: 145 year: 2016 ident: 10.1016/j.gmod.2023.101185_b9 article-title: Cross-class 3D object synthesis guided by reference examples publication-title: Comput. Graph. doi: 10.1016/j.cag.2015.06.009 – start-page: 610 year: 2022 ident: 10.1016/j.gmod.2023.101185_b18 article-title: The shape part slot machine: Contact-based reasoning for generating 3D shapes from parts – volume: 32 start-page: 1362 issue: 8 year: 2009 ident: 10.1016/j.gmod.2023.101185_b2 article-title: Accurate, dense, and robust multiview stereopsis publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2009.161 – ident: 10.1016/j.gmod.2023.101185_b5 doi: 10.1109/ICCV.2019.00885 – volume: 32 start-page: 69:1 issue: 4 year: 2013 ident: 10.1016/j.gmod.2023.101185_b27 article-title: Co-hierarchical analysis of shape structures publication-title: ACM Trans. Graph. doi: 10.1145/2461912.2461924 – start-page: 9:1 year: 2020 ident: 10.1016/j.gmod.2023.101185_b38 article-title: Contour-based 3D modeling through joint embedding of shapes and contours – start-page: 61 year: 2020 ident: 10.1016/j.gmod.2023.101185_b17 article-title: Coalesce: Component assembly by learning to synthesize connections – volume: 31 start-page: 180:1 issue: 6 year: 2012 ident: 10.1016/j.gmod.2023.101185_b42 article-title: Structure recovery by part assembly publication-title: ACM Trans. Graph. doi: 10.1145/2366145.2366199 – year: 2019 ident: 10.1016/j.gmod.2023.101185_b16 – volume: 36 start-page: 1 issue: 6 year: 2017 ident: 10.1016/j.gmod.2023.101185_b22 article-title: ComplementMe: Weakly-supervised component suggestions for 3D modeling publication-title: ACM Trans. Graph. doi: 10.1145/3130800.3130821 – volume: 30 start-page: 35:1 issue: 4 year: 2011 ident: 10.1016/j.gmod.2023.101185_b20 article-title: Probabilistic reasoning for assembly-based 3D modeling publication-title: ACM Trans. Graph. doi: 10.1145/2010324.1964930 – start-page: 115 year: 2014 ident: 10.1016/j.gmod.2023.101185_b28 article-title: Recurring part arrangements in shape collections – volume: 29 start-page: 183:1 issue: 6 year: 2010 ident: 10.1016/j.gmod.2023.101185_b12 article-title: Data-driven suggestions for creativity support in 3D modeling publication-title: ACM Trans. Graph. doi: 10.1145/1882261.1866205 – start-page: 553 year: 2011 ident: 10.1016/j.gmod.2023.101185_b25 article-title: Prior knowledge for part correspondence – volume: 28 start-page: 1758 issue: 4 year: 2022 ident: 10.1016/j.gmod.2023.101185_b39 article-title: FAME: 3D shape generation via functionality-aware model evolution publication-title: IEEE Trans. Vis. Comput. Graphics doi: 10.1109/TVCG.2020.3029759 – start-page: 97 year: 2008 ident: 10.1016/j.gmod.2023.101185_b11 article-title: Sketch-based search and composition of 3D models – ident: 10.1016/j.gmod.2023.101185_b1 doi: 10.1109/CVPR.2017.603 – start-page: 27 year: 2016 ident: 10.1016/j.gmod.2023.101185_b15 article-title: Structure-adaptive shape editing for man-made objects – year: 2015 ident: 10.1016/j.gmod.2023.101185_b41 – volume: 33 start-page: 34:1 issue: 4 year: 2014 ident: 10.1016/j.gmod.2023.101185_b14 article-title: Meta-representation of shape families publication-title: ACM Trans. Graph. doi: 10.1145/2601097.2601185 – volume: 32 start-page: 70:1 issue: 4 year: 2013 ident: 10.1016/j.gmod.2023.101185_b29 article-title: Learning part-based templates from large collections of 3D shapes publication-title: ACM Trans. Graph. doi: 10.1145/2461912.2461933 – start-page: 631 year: 2012 ident: 10.1016/j.gmod.2023.101185_b30 article-title: Exploring shape variations by 3d-model decomposition and part-based recombination – start-page: 1 year: 2021 ident: 10.1016/j.gmod.2023.101185_b7 – ident: 10.1016/j.gmod.2023.101185_b3 – volume: 33 start-page: 158:1 issue: 4 year: 2014 ident: 10.1016/j.gmod.2023.101185_b36 article-title: Topology-varying 3D shape creation via structural blending publication-title: ACM Trans. Graph. doi: 10.1145/2601097.2601102 – start-page: 129 year: 2007 ident: 10.1016/j.gmod.2023.101185_b21 article-title: Model composition from interchangeable components – start-page: 195 year: 2013 ident: 10.1016/j.gmod.2023.101185_b33 article-title: Smart variations: Functional substructures for part compatibility – volume: 23 start-page: 2574 issue: 12 year: 2017 ident: 10.1016/j.gmod.2023.101185_b8 article-title: Pose-inspired shape synthesis and functional hybrid publication-title: IEEE Trans. Vis. Comput. Graphics doi: 10.1109/TVCG.2017.2739159 – volume: 23 start-page: 652 year: 2004 ident: 10.1016/j.gmod.2023.101185_b10 article-title: Modeling by example publication-title: ACM Trans. Graph. doi: 10.1145/1015706.1015775 – volume: 30 start-page: 33:1 issue: 4 year: 2011 ident: 10.1016/j.gmod.2023.101185_b13 article-title: Exploration of continuous variability in collections of 3d shapes publication-title: ACM Trans. Graph. doi: 10.1145/2010324.1964928 – volume: 85 start-page: 1 year: 2016 ident: 10.1016/j.gmod.2023.101185_b34 article-title: Natural lines inspired 3D shape re-design publication-title: Graph. Models doi: 10.1016/j.gmod.2016.01.002 – ident: 10.1016/j.gmod.2023.101185_b19 doi: 10.1609/aaai.v34i07.6798 – start-page: 2690 year: 2019 ident: 10.1016/j.gmod.2023.101185_b40 article-title: Pix2Vox: Context-aware 3D reconstruction from single and multi-view images – start-page: 287 year: 2011 ident: 10.1016/j.gmod.2023.101185_b26 article-title: Symmetry hierarchy of man-made objects |
| SSID | ssj0011542 |
| Score | 2.352307 |
| Snippet | Assembling components of man-made objects to create new structures or complete 3D shapes is a popular approach in 3D modeling techniques. Recently, leveraging... |
| SourceID | doaj crossref elsevier |
| SourceType | Open Website Index Database Publisher |
| StartPage | 101185 |
| SubjectTerms | 3D modeling Generative autoencoder Shape completion Structure hybrid |
| Title | Component-aware generative autoencoder for structure hybrid and shape completion |
| URI | https://dx.doi.org/10.1016/j.gmod.2023.101185 https://doaj.org/article/85ab1d36d15541b6aabfb1966b6ec099 |
| Volume | 129 |
| WOSCitedRecordID | wos001046647500001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1524-0711 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0011542 issn: 1524-0703 databaseCode: DOA dateStart: 20230101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1524-0711 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0011542 issn: 1524-0703 databaseCode: AIEXJ dateStart: 20000101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV07T8MwELZQYYAB8RTlUXlgQxZxHk4yFlQEDFUHkLpFPj_aIpFWfYD49_jiBGWChSmSZdnW3cXfZ_n8HSHXAgIhQScsAlAsdpjDQEnLhJJ5DtpCLHyxiXQ4zMbjfNQq9YU5YV4e2BvuNkskcB0JjcDHQUgJFlzYCBBGOXqDu2-Q5s1hqr4_cMSguudMwphhUNfPZXxm1-R9jhqhYYQNHKsotyCpUu5vIVMLbR4OyH5NE2nfL--QbJnyiOy1xAOPyQh_5XnpQIPJT7k0dFIpSOP2ReVmPUeFSm2W1LFS6lViN67T9AufaFFZarqayoWhVU65QfeckNeHwcv9I6vrIzAVCb5mPBSWA1glIuUOg3Go0yyIolAby6UKALg0mbGa2zBxm14CaSYtUq7UcpulKjolndKt84xQLAardKZR395RNJA5j5X7JGmQSS6SLrlpTFQsvAxG0eSHvRVo0AINWniDdskdWvGnJ0pYVw3OsUXt2OIvx3ZJ0vigqNmAR3k31OyXyc__Y_ILsotD-qy9S9JxXjJXZEd9rGerZY9s958G4-deFXPflWbavg |
| linkProvider | Directory of Open Access Journals |
| 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=Component-aware+generative+autoencoder+for+structure+hybrid+and+shape+completion&rft.jtitle=Graphical+models&rft.au=Fan+Zhang&rft.au=Qiang+Fu&rft.au=Yang+Liu&rft.au=Xueming+Li&rft.date=2023-10-01&rft.pub=Elsevier&rft.issn=1524-0703&rft.volume=129&rft.spage=101185&rft_id=info:doi/10.1016%2Fj.gmod.2023.101185&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_85ab1d36d15541b6aabfb1966b6ec099 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1524-0703&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1524-0703&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1524-0703&client=summon |