EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
Locating 3D objects from a single RGB image via Perspective-n-Points (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest interpreting PnP as a differentiable layer, so that 2D-3D point correspondences can be partly learned by backpropagatin...
Saved in:
| Published in: | Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 2771 - 2780 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Conference Proceeding |
| Language: | English |
| Published: |
IEEE
01.06.2022
|
| Subjects: | |
| ISSN: | 1063-6919 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Locating 3D objects from a single RGB image via Perspective-n-Points (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest interpreting PnP as a differentiable layer, so that 2D-3D point correspondences can be partly learned by backpropagating the gradient w.r.t. object pose. Yet, learning the entire set of unrestricted 2D-3D points from scratch fails to converge with existing approaches, since the deterministic pose is inherently non-differentiable. In this paper, we propose the EPro-PnP a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose on the SE(3) manifold, essentially bringing categorical Softmax to the continuous domain. The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution. The underlying principle unifies the existing approaches and resembles the attention mechanism. EPro-PnP significantly outperforms competitive baselines, closing the gap between PnP-based method and the task-specific leaders on the LineMOD 6DoF pose estimation and nuScenes 3D object detection benchmarks. 3 |
|---|---|
| AbstractList | Locating 3D objects from a single RGB image via Perspective-n-Points (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning, recent studies suggest interpreting PnP as a differentiable layer, so that 2D-3D point correspondences can be partly learned by backpropagating the gradient w.r.t. object pose. Yet, learning the entire set of unrestricted 2D-3D points from scratch fails to converge with existing approaches, since the deterministic pose is inherently non-differentiable. In this paper, we propose the EPro-PnP a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose on the SE(3) manifold, essentially bringing categorical Softmax to the continuous domain. The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution. The underlying principle unifies the existing approaches and resembles the attention mechanism. EPro-PnP significantly outperforms competitive baselines, closing the gap between PnP-based method and the task-specific leaders on the LineMOD 6DoF pose estimation and nuScenes 3D object detection benchmarks. 3 |
| Author | Wang, Pichao Tian, Wei Chen, Hansheng Wang, Fan Xiong, Lu Li, Hao |
| Author_xml | – sequence: 1 givenname: Hansheng surname: Chen fullname: Chen, Hansheng email: hanshengchen97@gmail.com organization: School of Automotive Studies, Tongji University – sequence: 2 givenname: Pichao surname: Wang fullname: Wang, Pichao email: pichao.wang@alibaba-inc.com organization: Alibaba Group – sequence: 3 givenname: Fan surname: Wang fullname: Wang, Fan email: fan.w@alibaba-inc.com organization: Alibaba Group – sequence: 4 givenname: Wei surname: Tian fullname: Tian, Wei email: tian_wei@tongji.edu.cn organization: School of Automotive Studies, Tongji University – sequence: 5 givenname: Lu surname: Xiong fullname: Xiong, Lu email: xiong_lu@tongji.edu.cn organization: School of Automotive Studies, Tongji University – sequence: 6 givenname: Hao surname: Li fullname: Li, Hao email: lihao.lh@alibaba-inc.com organization: Alibaba Group |
| BookMark | eNotjctKAzEYhaMo2NY-gS7yAqm5zGQSd1LGKlQaRN2WXP7BlDEpk1HQp3dAV9_inO-cOTpLOQFC14yuGKP6Zv1mnmsulVpxyvmKUq7oCZozKetK6kqKUzRjVAoiNdMXaFnKgVIqOGNSqxl6b82QiUnmFm8gwWD7-AMBtymQMZMJeMqddbGPZYweGxjKEfwYv4AkYnJMY8FdHvBTTtl_9nbAO3eYCtjkAridpA87xpwu0Xln-wLLfy7Q6337sn4g293mcX23JZFTMRKw1nPtgTsLPAjKQtCscQCBuY7XnNoOVOWs0pb6RnkHvpKhq6BrJodpsUBXf7sRAPbHYbofvvdaNVpUtfgFZnxcAg |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/CVPR52688.2022.00280 |
| 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/IET Electronic Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences |
| EISBN | 1665469463 9781665469463 |
| EISSN | 1063-6919 |
| EndPage | 2780 |
| ExternalDocumentID | 9879345 |
| 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-i203t-eaac29ce2bae2d301dd917beed1bf2520afe84ba89a0c78cbec46df4ef7e2b193 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 110 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000867754203004&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 02:15:10 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i203t-eaac29ce2bae2d301dd917beed1bf2520afe84ba89a0c78cbec46df4ef7e2b193 |
| PageCount | 10 |
| ParticipantIDs | ieee_primary_9879345 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-June |
| PublicationDateYYYYMMDD | 2022-06-01 |
| PublicationDate_xml | – month: 06 year: 2022 text: 2022-June |
| PublicationDecade | 2020 |
| PublicationTitle | Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) |
| PublicationTitleAbbrev | CVPR |
| PublicationYear | 2022 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0003211698 |
| Score | 2.6019711 |
| Snippet | Locating 3D objects from a single RGB image via Perspective-n-Points (PnP) is a long-standing problem in computer vision. Driven by end-to-end deep learning,... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 2771 |
| SubjectTerms | 3D from single images; Computer vision theory; Deep learning architectures and techniques; Navigation and autonomous driving; Recognition: detection categorization Computer vision Deep learning Pose estimation Probabilistic logic retrieval; Robot vision; Statistical methods Robot vision systems Statistical analysis Three-dimensional displays |
| Title | EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation |
| URI | https://ieeexplore.ieee.org/document/9879345 |
| WOSCitedRecordID | wos000867754203004&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/eLvHCXMwlV09T8MwELXaioGpQIv4lgdGTFMnqW3WKhUDKhGCqltlxxeRJUFNysCv5-xERUgsTIkif0Q-nfzufO-ZkFsZZlOhM8VCDNuYU79jSscCDcIhABVE1ssXr57EcinXa5X2yN2eCwMAvvgM7t2rP8u3VbZzqbIJxscqjOI-6QshWq7WPp8SYiQzU7Jjx00DNZmv0hcnZuIKuDj3FZPBrztU_BayGP5v8iMy_uHi0XS_yxyTHpQnZNiBR9q5Zj0i7wm2YmmZPtBOSrr4wgZJaVlTMXy4UYzX03XSzDT9YVmykqVVUTY1RQRL0csrX5xKn41L0tC0qoEm2KllOY7J2yJ5nT-y7hoFVvAgbBhonXGVATcauEWHthZjNIO_PTU5j3mgc5CR0VLpIBMyQ6tGM5tHkAvsgwDvlAzKqoQzQnMT5jPJrQGpEclIFQuDECyG2B3ggz0nI7dwm49WKWPTrdnF358vyaGzTFt4dUUGzXYH1-Qg-2yKenvjzfsNEZKoaw |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELVKQYKpQIv4xgMjhtRJGpu1SlVEKREqVbfKji8iS4KalIFfzzmJWiGxMCWK_BH5dPK7871nQm6FG_cDFUvmYtjGrPodk8oP0CAcHJCOZyr54vkkmE7FYiGjFrnbcGEAoCo-g3v7Wp3lmzxe21TZA8bH0vX8HbLrex7v12ytTUbFxVhmIEXDj-s78mE4j96snIkt4eK8qpl0ft2iUm0io87_pj8kvS0bj0abfeaItCA7Jp0GPtLGOYsu-QixFYuy6JE2YtLpNzYIM8PKnOHDjqIrRV0rzkyjLc-SZSzK06wsKGJYin6eV-Wp9FXbNA2N8gJoiJ1qnmOPvI_C2XDMmosUWModt2SgVMxlDFwr4AZd2hiM0jT-dl8n3OeOSkB4WgmpnDgQMdrVG5jEgyTAPgjxTkg7yzM4JTTRbjIQ3GgQCrGMkH6gEYT54NsjfDBnpGsXbvlZa2UsmzU7__vzDdkfz14my8nT9PmCHFgr1WVYl6RdrtZwRfbirzItVteVqX8A_j-rsg |
| 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=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=EPro-PnP%3A+Generalized+End-to-End+Probabilistic+Perspective-n-Points+for+Monocular+Object+Pose+Estimation&rft.au=Chen%2C+Hansheng&rft.au=Wang%2C+Pichao&rft.au=Wang%2C+Fan&rft.au=Tian%2C+Wei&rft.date=2022-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=2771&rft.epage=2780&rft_id=info:doi/10.1109%2FCVPR52688.2022.00280&rft.externalDocID=9879345 |