DensePose: Dense Human Pose Estimation in the Wild
In this work we establish dense correspondences between an RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation. We gather dense correspondences for 50K persons appearing in the COCO dataset by introducing an efficient annotation pipeline....
Uložené v:
| Vydané v: | 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition s. 7297 - 7306 |
|---|---|
| Hlavní autori: | , , |
| Médium: | Konferenčný príspevok.. |
| Jazyk: | English |
| Vydavateľské údaje: |
IEEE
01.06.2018
|
| Predmet: | |
| ISSN: | 1063-6919 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | In this work we establish dense correspondences between an RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation. We gather dense correspondences for 50K persons appearing in the COCO dataset by introducing an efficient annotation pipeline. We then use our dataset to train CNN-based systems that deliver dense correspondence 'in the wild', namely in the presence of background, occlusions and scale variations. We improve our training set's effectiveness by training an inpainting network that can fill in missing ground truth values and report improvements with respect to the best results that would be achievable in the past. We experiment with fully-convolutional networks and region-based models and observe a superiority of the latter. We further improve accuracy through cascading, obtaining a system that delivers highly-accurate results at multiple frames per second on a single gpu. Supplementary materials, data, code, and videos are provided on the project page http://densepose.org. |
|---|---|
| AbstractList | In this work we establish dense correspondences between an RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation. We gather dense correspondences for 50K persons appearing in the COCO dataset by introducing an efficient annotation pipeline. We then use our dataset to train CNN-based systems that deliver dense correspondence 'in the wild', namely in the presence of background, occlusions and scale variations. We improve our training set's effectiveness by training an inpainting network that can fill in missing ground truth values and report improvements with respect to the best results that would be achievable in the past. We experiment with fully-convolutional networks and region-based models and observe a superiority of the latter. We further improve accuracy through cascading, obtaining a system that delivers highly-accurate results at multiple frames per second on a single gpu. Supplementary materials, data, code, and videos are provided on the project page http://densepose.org. |
| Author | Neverova, Natalia Guler, Riza Alp Kokkinos, Iasonas |
| Author_xml | – sequence: 1 givenname: Riza Alp surname: Guler fullname: Guler, Riza Alp – sequence: 2 givenname: Natalia surname: Neverova fullname: Neverova, Natalia – sequence: 3 givenname: Iasonas surname: Kokkinos fullname: Kokkinos, Iasonas |
| BookMark | eNotjjtPwzAURg0CibZkZmDxH0h6_Yh9zYZCoUiVqBCPsbKTizBqHVSHgX_f8Ji-T2c4OlN2kvpEjF0IqIQAN29e1o-VBIEVgDXyiBXOoqgVGqMluGM2EWBUaZxwZ6zI-QMApEGFup4weUMp07rPdMV_L19-7XziP4Qv8hB3foh94jHx4Z34a9x25-z0zW8zFf87Y8-3i6dmWa4e7u6b61UZpTBDGcgHp2yrKXQOO0GidSPDGjrSznTeEkpvwcsgANUYHDRKGWrXetcarWbs8s8biWjzuR9T9t8brC2iAXUA7HhF6A |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/CVPR.2018.00762 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences |
| EISBN | 9781538664209 1538664208 |
| EISSN | 1063-6919 |
| EndPage | 7306 |
| ExternalDocumentID | 8578860 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IH 6IL 6IN AAWTH ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP OCL RIE RIL RIO |
| ID | FETCH-LOGICAL-i216t-beab937c4ebd98d1e1c9bea850de496da7e82a70a2b1083153b4822b59ca9c643 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 935 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000457843607047&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 27 02:52:16 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i216t-beab937c4ebd98d1e1c9bea850de496da7e82a70a2b1083153b4822b59ca9c643 |
| OpenAccessLink | https://hal.science/hal-01951864 |
| PageCount | 10 |
| ParticipantIDs | ieee_primary_8578860 |
| PublicationCentury | 2000 |
| PublicationDate | 2018-Jun |
| PublicationDateYYYYMMDD | 2018-06-01 |
| PublicationDate_xml | – month: 06 year: 2018 text: 2018-Jun |
| PublicationDecade | 2010 |
| PublicationTitle | 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition |
| PublicationTitleAbbrev | CVPR |
| PublicationYear | 2018 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0002683845 ssj0003211698 |
| Score | 2.6480963 |
| Snippet | In this work we establish dense correspondences between an RGB image and a surface-based representation of the human body, a task we refer to as dense human... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 7297 |
| SubjectTerms | Deformable models Pipelines Pose estimation Solid modeling Task analysis Three-dimensional displays Training |
| Title | DensePose: Dense Human Pose Estimation in the Wild |
| URI | https://ieeexplore.ieee.org/document/8578860 |
| WOSCitedRecordID | wos000457843607047&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 | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05T8MwFLZKxcDE0SJueWAkNHF8spZWTFWEAHWr_OxnqUuKevD7sZOoMLCwPb_Jt793-SPkHgLK3AFkuUXMeMltZpWXmWfWShCAnkFDNqFmMz2fm6pHHva1MIjYJJ_hYxKbWL5fuV1ylY103F5aRgP9QCnV1mrt_SlM6lJ3EbLULqNlI43ufvMpcjMaf1SvKZcrJU-qxI7zi06leU2mx__rxwkZ_pTl0Wr_4JySHtZn5LjDkbQ7pZsBYc_RNsVqtcEn2oi0cdXTpKGTeKbbckW6rGmEfzReDH5I3qeTt_FL1nEjZEtWyG0GaCEiC8cRvNG-wMKZqNMi98iN9FahZlbllkGRyMRECTxiARDGWeMiDDkn_XpV4wWhFoSQPJTSIecYCihFCMnQAwwyaHNJBmkKFp_t9xeLbvRXf6uvyVGa4zab6ob0t-sd3pJD97VdbtZ3zZp9A8e0l4g |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELaqggRTgRbxxgMjoYljOzZraVVEqSJUULfKZ1-kLi3qg9-PnUSFgYXtfJPf_u7lj5A7KFDGFiCKDWLEU24ikzkZOWaMBAHoGJRkE9l4rKZTnTfI_a4WBhHL5DN8CGIZy3dLuw2usq7y20tJb6DvCc5ZUlVr7TwqTKpU1TGy0E69bSO1qv_zSWLd7X3kbyGbK6RPZoEf5xehSvmeDFr_68kR6fwU5tF89-QckwYuTkirRpK0PqfrNmFP3jrFfLnGR1qKtHTW06ChfX-qq4JFOl9QDwCpvxpch7wP-pPeMKrZEaI5S-QmAjTgsYXlCE4rl2BitdcpETvkWjqToWImiw2DJNCJiRS4RwMgtDXaeiBySpqL5QLPCDUghORFKi1yjkUCqSiKYOoBFrJQ-py0wxTMPqsPMGb16C_-Vt-Sg-HkdTQbPY9fLslhmO8qt-qKNDerLV6Tffu1ma9XN-X6fQPd1JrP |
| 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%3Abook&rft.genre=proceeding&rft.title=2018+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.atitle=DensePose%3A+Dense+Human+Pose+Estimation+in+the+Wild&rft.au=Guler%2C+Riza+Alp&rft.au=Neverova%2C+Natalia&rft.au=Kokkinos%2C+Iasonas&rft.date=2018-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=7297&rft.epage=7306&rft_id=info:doi/10.1109%2FCVPR.2018.00762&rft.externalDocID=8578860 |