High-Fidelity Monocular Face Reconstruction Based on an Unsupervised Model-Based Face Autoencoder
In this work, we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional encoder network with an expert-designed generative model that ser...
Uložené v:
| Vydané v: | IEEE transactions on pattern analysis and machine intelligence Ročník 42; číslo 2; s. 357 - 370 |
|---|---|
| Hlavní autori: | , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
United States
IEEE
01.02.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Predmet: | |
| ISSN: | 0162-8828, 1939-3539, 2160-9292, 1939-3539 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | In this work, we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional encoder network with an expert-designed generative model that serves as decoder. The core innovation is the differentiable parametric decoder that encapsulates image formation analytically based on a generative model. Our decoder takes as input a code vector with exactly defined semantic meaning that encodes detailed face pose, shape, expression, skin reflectance, and scene illumination. Due to this new way of combining CNN-based with model-based face reconstruction, the CNN-based encoder learns to extract semantically meaningful parameters from a single monocular input image. For the first time, a CNN encoder and an expert-designed generative model can be trained end-to-end in an unsupervised manner, which renders training on very large (unlabeled) real world datasets feasible. The obtained reconstructions compare favorably to current state-of-the-art approaches in terms of quality and richness of representation. This work is an extended version of [1] , where we additionally present a stochastic vertex sampling technique for faster training of our networks, and moreover, we propose and evaluate analysis-by-synthesis and shape-from-shading refinement approaches to achieve a high-fidelity reconstruction. |
|---|---|
| AbstractList | In this work, we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional encoder network with an expert-designed generative model that serves as decoder. The core innovation is the differentiable parametric decoder that encapsulates image formation analytically based on a generative model. Our decoder takes as input a code vector with exactly defined semantic meaning that encodes detailed face pose, shape, expression, skin reflectance, and scene illumination. Due to this new way of combining CNN-based with model-based face reconstruction, the CNN-based encoder learns to extract semantically meaningful parameters from a single monocular input image. For the first time, a CNN encoder and an expert-designed generative model can be trained end-to-end in an unsupervised manner, which renders training on very large (unlabeled) real world datasets feasible. The obtained reconstructions compare favorably to current state-of-the-art approaches in terms of quality and richness of representation. This work is an extended version of [1] , where we additionally present a stochastic vertex sampling technique for faster training of our networks, and moreover, we propose and evaluate analysis-by-synthesis and shape-from-shading refinement approaches to achieve a high-fidelity reconstruction. In this work, we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional encoder network with an expert-designed generative model that serves as decoder. The core innovation is the differentiable parametric decoder that encapsulates image formation analytically based on a generative model. Our decoder takes as input a code vector with exactly defined semantic meaning that encodes detailed face pose, shape, expression, skin reflectance, and scene illumination. Due to this new way of combining CNN-based with model-based face reconstruction, the CNN-based encoder learns to extract semantically meaningful parameters from a single monocular input image. For the first time, a CNN encoder and an expert-designed generative model can be trained end-to-end in an unsupervised manner, which renders training on very large (unlabeled) real world datasets feasible. The obtained reconstructions compare favorably to current state-of-the-art approaches in terms of quality and richness of representation. This work is an extended version of [1] , where we additionally present a stochastic vertex sampling technique for faster training of our networks, and moreover, we propose and evaluate analysis-by-synthesis and shape-from-shading refinement approaches to achieve a high-fidelity reconstruction.In this work, we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional encoder network with an expert-designed generative model that serves as decoder. The core innovation is the differentiable parametric decoder that encapsulates image formation analytically based on a generative model. Our decoder takes as input a code vector with exactly defined semantic meaning that encodes detailed face pose, shape, expression, skin reflectance, and scene illumination. Due to this new way of combining CNN-based with model-based face reconstruction, the CNN-based encoder learns to extract semantically meaningful parameters from a single monocular input image. For the first time, a CNN encoder and an expert-designed generative model can be trained end-to-end in an unsupervised manner, which renders training on very large (unlabeled) real world datasets feasible. The obtained reconstructions compare favorably to current state-of-the-art approaches in terms of quality and richness of representation. This work is an extended version of [1] , where we additionally present a stochastic vertex sampling technique for faster training of our networks, and moreover, we propose and evaluate analysis-by-synthesis and shape-from-shading refinement approaches to achieve a high-fidelity reconstruction. |
| Author | Kim, Hyeongwoo Perez, Patrick Zollhofer, Michael Tewari, Ayush Bernard, Florian Theobalt, Christian Garrido, Pablo |
| Author_xml | – sequence: 1 givenname: Ayush orcidid: 0000-0002-3805-4421 surname: Tewari fullname: Tewari, Ayush email: atewari@mpi-inf.mpg.de organization: Max-Planck-Institute for Informatics, Saarbrcken, Germany – sequence: 2 givenname: Michael surname: Zollhofer fullname: Zollhofer, Michael email: zollhoefer@cs.stanford.edu organization: Stanford University, Stanford, CA, USA – sequence: 3 givenname: Florian surname: Bernard fullname: Bernard, Florian email: f.bernardpi@gmail.com organization: Max-Planck-Institute for Informatics, Saarbrcken, Germany – sequence: 4 givenname: Pablo surname: Garrido fullname: Garrido, Pablo email: pablo.garrido.adrian@gmail.com organization: Technicolor, Issy-les-Moulineaux, France – sequence: 5 givenname: Hyeongwoo orcidid: 0000-0003-0858-0882 surname: Kim fullname: Kim, Hyeongwoo email: hyeongwoo.kim@mpi-inf.mpg.de organization: Max-Planck-Institute for Informatics, Saarbrcken, Germany – sequence: 6 givenname: Patrick surname: Perez fullname: Perez, Patrick email: Patrick.Perez@technicolor.com organization: Technicolor, Issy-les-Moulineaux, France – sequence: 7 givenname: Christian surname: Theobalt fullname: Theobalt, Christian email: theobalt@mpi-inf.mpg.de organization: Max-Planck-Institute for Informatics, Saarbrcken, Germany |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30334783$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kc1q3DAURkVJaCY_L9BCMWTTjaeSri3Ly2noNIEMLSVZC_nOdavgkaaSXcjbR5OZZpFFVhKfzpHE_U7ZkQ-eGPsg-FwI3n65-7lY3cwlF3oudaN0Jd-xmRSKl61s5RGbcaFkqbXUJ-w0pQfORVVzeM9OgANUjYYZs9fu959y6dY0uPGxWAUfcBpsLJYWqfhFGHwa44SjC774ahOti7yxvrj3adpS_Od20Spkv9wfP4uLaQzkMcfxnB33dkh0cVjP2P3y293VdXn74_vN1eK2RKjFWFpQpFBYQFW1ogHUPXRSWqAGAaHv2k42Pe8QO2g0AvRa6XWlCVUOeAtn7PP-3m0MfydKo9m4hDQM1lOYkpFCyrpptKwzevkKfQhT9Pl3RgK0ADUXPFOfDtTUbWhtttFtbHw0_4eXAbkHMIaUIvUviOBm15B5bsjsGjKHhrKkX0noRrsb7xitG95WP-5VR0Qvb-mqVTrX-gSpj51M |
| CODEN | ITPIDJ |
| CitedBy_id | crossref_primary_10_1109_TVCG_2022_3166666 crossref_primary_10_1016_j_cose_2024_104217 crossref_primary_10_1016_j_cosrev_2021_100400 crossref_primary_10_1109_TVCG_2020_3033838 crossref_primary_10_1007_s11554_023_01257_z crossref_primary_10_3390_rs15225404 crossref_primary_10_1109_ACCESS_2025_3551397 crossref_primary_10_1109_TIM_2022_3152243 crossref_primary_10_1016_j_media_2022_102730 crossref_primary_10_1007_s41095_021_0238_4 crossref_primary_10_1016_j_cviu_2022_103525 crossref_primary_10_1109_TPAMI_2019_2920821 crossref_primary_10_1109_TPAMI_2021_3084524 crossref_primary_10_1186_s12903_023_03142_4 crossref_primary_10_1109_TIP_2021_3065798 crossref_primary_10_1109_TPAMI_2025_3562651 crossref_primary_10_3389_fams_2022_869830 crossref_primary_10_1007_s10462_021_10039_7 crossref_primary_10_1111_cgf_14400 crossref_primary_10_1109_JIOT_2021_3114373 crossref_primary_10_1007_s00371_023_02946_3 crossref_primary_10_1016_j_patrec_2021_11_022 crossref_primary_10_1109_TVCG_2020_3023573 crossref_primary_10_1051_itmconf_20224403024 crossref_primary_10_1109_ACCESS_2023_3324403 crossref_primary_10_1016_j_imavis_2021_104311 crossref_primary_10_3390_app13116407 crossref_primary_10_1109_TMC_2023_3262233 crossref_primary_10_1109_TCYB_2023_3242368 |
| Cites_doi | 10.1145/2647868.2654889 10.1109/ICCVW.2015.126 10.1007/978-3-642-15549-9_25 10.1631/FITEE.1700253 10.1109/TPAMI.2011.172 10.20870/IJVR.2010.9.1.2761 10.1016/j.cviu.2015.01.008 10.1109/CVPR.2017.250 10.1007/978-3-319-46448-0_3 10.1109/CVPR.2011.5995388 10.1109/TIFS.2015.2446438 10.1109/CVPR.2017.44 10.1109/TMM.2015.2477042 10.1109/CVPR.2005.145 10.1109/ICCVW.2017.110 10.1145/2661229.2661290 10.1109/ICCV.2017.175 10.1145/1778765.1778777 10.1109/34.927467 10.1109/ICCV.2017.117 10.1007/978-3-642-21735-7_7 10.1145/3099564.3099581 10.1109/ICCV.2013.21 10.1109/ICCVW.2013.58 10.1007/s11263-010-0408-9 10.1109/CVPR.2013.446 10.1007/978-3-319-46454-1_37 10.1109/CVPR.2014.243 10.1109/CVPR.2017.589 10.1109/CVPR.2017.164 10.1007/s11263-010-0380-4 10.1109/CVPR.2017.580 10.1109/3DV.2016.56 10.1145/2929464.2929475 10.1007/978-3-540-87536-9_99 10.1109/ICCV.2015.450 10.1007/978-3-319-46448-0_21 10.1145/311535.311556 10.1109/TVCG.2013.249 10.1109/CVPR.2018.00877 10.1109/CVPR.2015.7298989 10.1109/ICPR.2016.7899665 10.1111/1467-8659.t01-1-00712 10.1007/BFb0094775 10.1109/CVPR.2016.455 10.1145/2766943 10.1145/2508363.2508380 10.1145/1667239.1667251 10.1109/CVPR.2017.163 10.1109/ICCV.2015.425 10.1126/science.1127647 10.1145/1964921.1964970 10.1109/CVPR.2018.00486 10.1109/ICCV.2011.6126439 10.1145/1015706.1015736 10.1007/978-3-319-10605-2_1 10.1109/ICCVW.2015.132 10.1145/2897824.2925933 10.1109/CVPR.2018.00270 10.1016/j.cviu.2017.08.008 10.1007/978-3-319-49409-8_9 10.1109/ICCV.2017.429 10.1007/s11263-014-0775-8 |
| 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 CGR CUY CVF ECM EIF NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TPAMI.2018.2876842 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE 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 MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) 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 | MEDLINE Technology Research Database 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/IET Electronic Library (IEL) (UW System Shared) 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 | 370 |
| ExternalDocumentID | 30334783 10_1109_TPAMI_2018_2876842 8496850 |
| Genre | orig-research Research Support, Non-U.S. Gov't Journal Article |
| GrantInformation_xml | – fundername: Max Planck Center for Visual Computing and Communications – fundername: ERC Starting grantid: CapReal 335545 |
| GroupedDBID | --- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB ~02 AAYXX CITATION 5VS 9M8 AAYOK ABFSI ADRHT AETIX AGSQL AI. AIBXA ALLEH CGR CUY CVF ECM EIF FA8 H~9 IBMZZ ICLAB IFJZH NPM PKN RIC RIG RNI RZB VH1 XJT Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c351t-a36e6c1a3c649173c8f3b22a3e7c3c3fb9b27f0bccb378c33f868d48ec6b37093 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 41 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000508386100009&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 | Sun Nov 09 10:32:04 EST 2025 Sun Nov 30 04:32:43 EST 2025 Wed Feb 19 02:29:27 EST 2025 Sat Nov 29 05:15:58 EST 2025 Tue Nov 18 21:49:20 EST 2025 Wed Aug 27 02:40:53 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| 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-c351t-a36e6c1a3c649173c8f3b22a3e7c3c3fb9b27f0bccb378c33f868d48ec6b37093 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-3805-4421 0000-0003-0858-0882 |
| PMID | 30334783 |
| PQID | 2339335010 |
| PQPubID | 85458 |
| PageCount | 14 |
| ParticipantIDs | crossref_primary_10_1109_TPAMI_2018_2876842 ieee_primary_8496850 proquest_journals_2339335010 crossref_citationtrail_10_1109_TPAMI_2018_2876842 proquest_miscellaneous_2122577825 pubmed_primary_30334783 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-02-01 |
| PublicationDateYYYYMMDD | 2020-02-01 |
| PublicationDate_xml | – month: 02 year: 2020 text: 2020-02-01 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 | 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 kulkarni (ref19) 2015 ref12 ref59 ref15 ref58 ref14 ref53 ref52 zhu (ref36) 2014 ref55 ref11 ref10 huang (ref68) 2007 ref17 parkhi (ref70) 2015 zhao (ref18) 2016 tang (ref34) 2012 ref51 ref50 duong (ref39) 2016 ref46 ref89 ref45 ref48 tewari (ref1) 2017 ref47 ref86 ref42 ref85 ref41 huber (ref25) 2016 ref88 ref44 ref43 (ref74) 2008 güler (ref38) 2016 ref7 ref4 ref3 grant (ref20) 2016 hinton (ref16) 2006; 313 ref6 ref5 ref82 garrido (ref87) 2013; 32 ref81 ref40 cao (ref71) 2014; 20 bulat (ref32) 2016 ref80 ref79 ref35 ref75 ref31 ref30 ref77 ref76 ref2 suwajanakorn (ref9) 2014 garrido (ref8) 2016; 35 tylecek (ref83) 2010; 9 krizhevsky (ref69) 2012 yan (ref56) 2016 ref73 jaderberg (ref54) 2015 zhmoginov (ref49) 2016 ref24 ref67 ref23 ref64 ref63 ref66 ref22 (ref78) 2012 ref65 ref21 li (ref37) 2016 ref28 ref27 ref29 ranjan (ref33) 2016 cao (ref60) 2014; 20 cao (ref84) 2015; 34 wang (ref26) 2014 bradski (ref72) 2000; 25 ref62 ref61 |
| References_xml | – ident: ref73 doi: 10.1145/2647868.2654889 – ident: ref65 doi: 10.1109/ICCVW.2015.126 – ident: ref11 doi: 10.1007/978-3-642-15549-9_25 – ident: ref21 doi: 10.1631/FITEE.1700253 – ident: ref82 doi: 10.1109/TPAMI.2011.172 – volume: 9 start-page: 45 year: 2010 ident: ref83 article-title: Refinement of surface mesh for accurate multiview reconstruction publication-title: Int J Virtual Reality doi: 10.20870/IJVR.2010.9.1.2761 – ident: ref89 doi: 10.1016/j.cviu.2015.01.008 – ident: ref43 doi: 10.1109/CVPR.2017.250 – ident: ref31 doi: 10.1007/978-3-319-46448-0_3 – ident: ref81 doi: 10.1109/CVPR.2011.5995388 – start-page: 2017 year: 2015 ident: ref54 article-title: Spatial transformer networks publication-title: Proc Int Conf Neural Inf Process – ident: ref52 doi: 10.1109/TIFS.2015.2446438 – year: 2015 ident: ref70 article-title: Deep face recognition publication-title: Proc Brit Mach Vis Conf – year: 2014 ident: ref26 article-title: Facial feature point detection: A comprehensive survey publication-title: CoRR – year: 2016 ident: ref33 article-title: An all-in-one convolutional neural network for face analysis – ident: ref46 doi: 10.1109/CVPR.2017.44 – start-page: 1419 year: 2012 ident: ref34 article-title: Deep lambertian networks publication-title: Proc Int Conf Int Conf Mach Learn – ident: ref53 doi: 10.1109/TMM.2015.2477042 – start-page: 2539 year: 2015 ident: ref19 article-title: Deep convolutional inverse graphics network publication-title: Proc Int Conf Neural Inf Process – ident: ref24 doi: 10.1109/CVPR.2005.145 – ident: ref75 doi: 10.1109/CVPR.2005.145 – ident: ref57 doi: 10.1109/ICCVW.2017.110 – ident: ref88 doi: 10.1145/2661229.2661290 – ident: ref15 doi: 10.1109/ICCV.2017.175 – ident: ref85 doi: 10.1145/1778765.1778777 – volume: 35 year: 2016 ident: ref8 article-title: Reconstruction of personalized 3D face rigs from monocular video publication-title: ACM Trans Graph – ident: ref22 doi: 10.1109/34.927467 – ident: ref45 doi: 10.1109/ICCV.2017.117 – ident: ref17 doi: 10.1007/978-3-642-21735-7_7 – ident: ref41 doi: 10.1145/3099564.3099581 – year: 2016 ident: ref38 article-title: DenseReg: Fully convolutional dense shape regression in-the-wild publication-title: CoRR – ident: ref35 doi: 10.1109/ICCV.2013.21 – ident: ref29 doi: 10.1109/ICCVW.2013.58 – year: 2007 ident: ref68 article-title: Labeled faces in the wild: A database for studying face recognition in unconstrained environments – ident: ref80 doi: 10.1007/s11263-010-0408-9 – ident: ref28 doi: 10.1109/CVPR.2013.446 – year: 2008 ident: ref74 article-title: NVIDIA CUDA Programming Guide 2.0 – ident: ref42 doi: 10.1007/978-3-319-46454-1_37 – year: 2012 ident: ref78 publication-title: CUBLAS Library User Guide v5 0 ed nVidia – ident: ref50 doi: 10.1109/CVPR.2014.243 – ident: ref13 doi: 10.1109/CVPR.2017.589 – ident: ref47 doi: 10.1109/CVPR.2017.164 – ident: ref63 doi: 10.1007/s11263-010-0380-4 – ident: ref23 doi: 10.1109/CVPR.2017.580 – ident: ref12 doi: 10.1109/3DV.2016.56 – ident: ref4 doi: 10.1145/2929464.2929475 – ident: ref48 doi: 10.1007/978-3-540-87536-9_99 – year: 2016 ident: ref25 article-title: 3D face tracking and texture fusion in the wild publication-title: CoRR – ident: ref10 doi: 10.1109/ICCV.2015.450 – ident: ref79 doi: 10.1007/978-3-319-46448-0_21 – year: 2016 ident: ref37 article-title: Convolutional network for attribute-driven and identity-preserving human face generation publication-title: CoRR – start-page: 1097 year: 2012 ident: ref69 article-title: ImageNet classification with deep convolutional neural networks publication-title: Proc Int Conf Neural Inf Process – ident: ref5 doi: 10.1145/311535.311556 – start-page: 616 year: 2016 ident: ref32 article-title: Two-stage convolutional part heatmap regression for the 1st 3D face alignment in the wild (3DFAW) challenge publication-title: Proc Eur Conf Comput Vis Workshops – volume: 20 start-page: 413 year: 2014 ident: ref60 article-title: FaceWarehouse: A 3D facial expression database for visual computing publication-title: IEEE Trans Vis Comput Graph doi: 10.1109/TVCG.2013.249 – ident: ref44 doi: 10.1109/CVPR.2018.00877 – ident: ref67 doi: 10.1109/CVPR.2015.7298989 – ident: ref40 doi: 10.1109/ICPR.2016.7899665 – ident: ref6 doi: 10.1111/1467-8659.t01-1-00712 – ident: ref62 doi: 10.1007/BFb0094775 – ident: ref3 doi: 10.1109/CVPR.2016.455 – year: 2016 ident: ref49 article-title: Inverting face embeddings with convolutional neural networks publication-title: CoRR – year: 2016 ident: ref18 article-title: Robust LSTM-autoencoders for face de-occlusion in the wild publication-title: CoRR – volume: 34 start-page: 46:1 year: 2015 ident: ref84 article-title: Real-time high-fidelity facial performance capture publication-title: ACM Trans Graph doi: 10.1145/2766943 – volume: 32 start-page: 158:1 year: 2013 ident: ref87 article-title: Reconstructing detailed dynamic face geometry from monocular video publication-title: ACM Trans Graph doi: 10.1145/2508363.2508380 – ident: ref59 doi: 10.1145/1667239.1667251 – ident: ref14 doi: 10.1109/CVPR.2017.163 – year: 2016 ident: ref39 article-title: Deep appearance models: A deep Boltzmann machine approach for face modeling publication-title: CoRR – start-page: 3735 year: 2017 ident: ref1 article-title: MoFA: Model-based deep convolutional face autoencoder for unsupervised monocular reconstruction publication-title: Proc Int Conf Comput Vis – ident: ref64 doi: 10.1109/ICCV.2015.425 – volume: 313 start-page: 504 year: 2006 ident: ref16 article-title: Reducing the dimensionality of data with neural networks publication-title: Sci doi: 10.1126/science.1127647 – ident: ref86 doi: 10.1145/1964921.1964970 – ident: ref77 doi: 10.1109/CVPR.2018.00486 – ident: ref2 doi: 10.1109/ICCV.2011.6126439 – start-page: 796 year: 2014 ident: ref9 article-title: Total moving face reconstruction publication-title: Proc Eur Conf Comput Vis – volume: 20 start-page: 413 year: 2014 ident: ref71 article-title: FaceWarehouse: A 3D facial expression database for visual computing publication-title: IEEE Trans Vis Comput Graph doi: 10.1109/TVCG.2013.249 – ident: ref61 doi: 10.1145/1015706.1015736 – start-page: 266 year: 2016 ident: ref20 article-title: Deep disentangled representations for volumetric reconstruction publication-title: Proc Eur Conf Comput Vis Workshops – ident: ref51 doi: 10.1007/978-3-319-10605-2_1 – ident: ref66 doi: 10.1109/ICCVW.2015.132 – ident: ref7 doi: 10.1145/2897824.2925933 – ident: ref76 doi: 10.1109/CVPR.2018.00270 – start-page: 1696 year: 2016 ident: ref56 article-title: Perspective transformer nets: Learning single-view 3D object reconstruction without 3D supervision publication-title: Adv Neural Inf Process Syst – start-page: 217 year: 2014 ident: ref36 article-title: Multi-view perceptron: A deep model for learning face identity and view representations publication-title: Proc 27th Int Conf Neural Inf Process Syst – ident: ref27 doi: 10.1016/j.cviu.2017.08.008 – ident: ref55 doi: 10.1007/978-3-319-49409-8_9 – ident: ref58 doi: 10.1109/ICCV.2017.429 – ident: ref30 doi: 10.1007/s11263-014-0775-8 – volume: 25 start-page: 120 year: 2000 ident: ref72 article-title: The OpenCV library publication-title: Dr Dobb's J Softw Tools |
| SSID | ssj0014503 |
| Score | 2.5622318 |
| Snippet | In this work, we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 357 |
| SubjectTerms | Accuracy Coders Color imagery Decoding Deep Learning Face Face - anatomy & histology Face - diagnostic imaging Female Humans Image reconstruction Imaging, Three-Dimensional - methods Lighting Male Neural Networks, Computer Shading Shape Three-dimensional displays Training Unsupervised Machine Learning |
| Title | High-Fidelity Monocular Face Reconstruction Based on an Unsupervised Model-Based Face Autoencoder |
| URI | https://ieeexplore.ieee.org/document/8496850 https://www.ncbi.nlm.nih.gov/pubmed/30334783 https://www.proquest.com/docview/2339335010 https://www.proquest.com/docview/2122577825 |
| Volume | 42 |
| WOSCitedRecordID | wos000508386100009&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/IET Electronic Library (IEL) (UW System Shared) 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/eLvHCXMwlV3db9QwDLfGhNB4YLDxcTCmIPEG3Xp10yaPB-IEEkx72NC9VYmbSkhTO-3u9vfPTj8ACZB4ixKnrWo78S92bIC36LT2ZG3ijTYMULRLXK4poSbFDOvMm3im-_1reXZmVit7vgPvp7swIYQYfBZOpBl9-XVHWzkqOzW5LYwA9HtlWfR3tSaPQa5jFWS2YFjDGUaMF2RSe3pxvvj2RaK4zAnjA3E87cEDXroxLw3-th_FAit_tzXjnrPc_7-vfQyPBttSLXpheAI7oT2A_bFugxrU-AAe_pKE8BCchHokS0l3xRa5YiXvYmyqWjoKSuDpzySz6gNverXihmvVZbveXstSI11SU-0q6YfjxMV200mSzDrcPIXL5aeLj5-TofBCQqjnm8RhEQqaO6QiZziHZBr0WeYwlISEjbc-K5vUE3ksDSE2pjB1bgIV3JFafAa7bdeGF6Bc1oTQGCw8IzdNTJ050nKBl8gW1s9gPv7-ioas5FIc46qK6CS1VeReJdyrBu7N4N0057rPyfFP6kPhzUQ5sGUGRyOXq0Ft11WGaFFcrTz8ZhpmhRMvimtDt2WaOS-BJRtWegbPe-mYnj0K1cs_v_MV7GUC12PQ9xHsMvPCa7hPt5sf65tjluqVOY5SfQced_Bs |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB5VBUE5UGh5LBQwEjdIm_XEiX1cEKtWbFc9bFFvkT1xJKQqqbq7_H7GzgOQAImbZY-TKOOx5_O8AN6hVcqRMYnTSjNAUTaxmaKE6hQlVtLpeKf7dVEsl_rqylzswIcxFsZ7H53P_HFoRlt-1dI2XJWd6MzkOgD0OyrLZNpFa402g0zFOsisw7CMM5AYQmRSc7K6mJ2fBT8ufcwIIZie9uAeb96YFRp_O5FiiZW_a5vx1Jnv_9_3PoKHvXYpZt1yeAw7vjmA_aFyg-gF-QAe_JKG8BBscPZI5iHhFevkgsW8jd6pYm7JiwBQf6aZFR_52KsEN2wjLpv19iZsNqErVFW7TrrhOHG23bQhTWblb5_A5fzz6tNp0pdeSAjVdJNYzH1OU4uUZwzokHSNTkqLviAkrJ1xsqhTR-Sw0IRY61xXmfaUc0dq8CnsNm3jn4Owsva-1pg7xm6KmFpaUiGEl8jkxk1gOvz-kvq85KE8xnUZ8Ulqysi9MnCv7Lk3gffjnJsuK8c_qQ8Db0bKni0TOBq4XPaCuy4losFgbOXht-Mwi1ywo9jGt1ummfImWLBqpSbwrFsd47OHRfXiz-98A_dPV-eLcnG2_PIS9mQA79EF_Ah2mZH-Fdyl75tv69vXcW3_ABoB8ss |
| 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=High-Fidelity+Monocular+Face+Reconstruction+Based+on+an+Unsupervised+Model-Based+Face+Autoencoder&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Tewari%2C+Ayush&rft.au=Zollhofer%2C+Michael&rft.au=Bernard%2C+Florian&rft.au=Garrido%2C+Pablo&rft.date=2020-02-01&rft.issn=0162-8828&rft.eissn=2160-9292&rft.volume=42&rft.issue=2&rft.spage=357&rft.epage=370&rft_id=info:doi/10.1109%2FTPAMI.2018.2876842&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TPAMI_2018_2876842 |
| 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 |