What Do Single-View 3D Reconstruction Networks Learn?

Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research. All existing techniques are united by the idea of having an encoder-decoder network that performs non-trivial reasoning about the 3D structure of the output s...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 3400 - 3409
Hlavní autoři: Tatarchenko, Maxim, Richter, Stephan R., Ranftl, Rene, Li, Zhuwen, Koltun, Vladlen, Brox, Thomas
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2019
Témata:
3D from Single Image
Cognition
Computer vision
Convolutional neural networks
Coordinate measuring machines
Deep Learning
Image classification
Image reconstruction
Pattern recognition
Three-dimensional displays
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research. All existing techniques are united by the idea of having an encoder-decoder network that performs non-trivial reasoning about the 3D structure of the output space. In this work, we set up two alternative approaches that perform image classification and retrieval respectively. These simple baselines yield better results than state-of-the-art methods, both qualitatively and quantitatively. We show that encoder-decoder methods are statistically indistinguishable from these baselines, thus indicating that the current state of the art in single-view object reconstruction does not actually perform reconstruction but image classification. We identify aspects of popular experimental procedures that elicit this behavior and discuss ways to improve the current state of research.
AbstractList Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research. All existing techniques are united by the idea of having an encoder-decoder network that performs non-trivial reasoning about the 3D structure of the output space. In this work, we set up two alternative approaches that perform image classification and retrieval respectively. These simple baselines yield better results than state-of-the-art methods, both qualitatively and quantitatively. We show that encoder-decoder methods are statistically indistinguishable from these baselines, thus indicating that the current state of the art in single-view object reconstruction does not actually perform reconstruction but image classification. We identify aspects of popular experimental procedures that elicit this behavior and discuss ways to improve the current state of research.
Author Richter, Stephan R.
Brox, Thomas
Ranftl, Rene
Li, Zhuwen
Tatarchenko, Maxim
Koltun, Vladlen
Author_xml – sequence: 1
  givenname: Maxim
  surname: Tatarchenko
  fullname: Tatarchenko, Maxim
  organization: Freiburg
– sequence: 2
  givenname: Stephan R.
  surname: Richter
  fullname: Richter, Stephan R.
  organization: Intel Labs
– sequence: 3
  givenname: Rene
  surname: Ranftl
  fullname: Ranftl, Rene
  organization: Intel Labs
– sequence: 4
  givenname: Zhuwen
  surname: Li
  fullname: Li, Zhuwen
  organization: Pony AI
– sequence: 5
  givenname: Vladlen
  surname: Koltun
  fullname: Koltun, Vladlen
  organization: Intel Labs
– sequence: 6
  givenname: Thomas
  surname: Brox
  fullname: Brox, Thomas
  organization: Univ. of Freiburg
BookMark eNotjstKw0AUQEdRsNasXbiZH0idO3cmmbsSSesDgkrVuizzikbrRJJI8e8t6OpsDodzzA5SlyJjpyBmAILOq9XDciYF0EwI1HKPZVQaKKUBlIRmn01AFJgXBHTEsmF4FztPAhRkJky_vNmRzzv-2KbXTcxXbdxynPNl9F0axv7bj22X-F0ct13_MfA62j5dnLDDxm6GmP1zyp6vFk_VTV7fX99Wl3XeSoFjrozDQB618sEh2N1uSdigDEa7gI2RpY_CNqoM2jpltHDCEQbpjWwUFThlZ3_dNsa4_urbT9v_rA1pBRLwF6IaRnM
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2019.00352
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore
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 9781728132938
1728132932
EISSN 1063-6919
EndPage 3409
ExternalDocumentID 8954121
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-48b3d9c354cdb31a110793f32d85bd3f827ce0af47d5ab4850b0b93d2c82f4963
IEDL.DBID RIE
ISICitedReferencesCount 330
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000529484003059&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Sep 10 07:40:26 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-48b3d9c354cdb31a110793f32d85bd3f827ce0af47d5ab4850b0b93d2c82f4963
PageCount 10
ParticipantIDs ieee_primary_8954121
PublicationCentury 2000
PublicationDate 2019-June
PublicationDateYYYYMMDD 2019-06-01
PublicationDate_xml – month: 06
  year: 2019
  text: 2019-June
PublicationDecade 2010
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.6108272
Snippet Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research. All existing...
SourceID ieee
SourceType Publisher
StartPage 3400
SubjectTerms 3D from Single Image
Cognition
Computer vision
Convolutional neural networks
Coordinate measuring machines
Deep Learning
Image classification
Image reconstruction
Pattern recognition
Three-dimensional displays
Title What Do Single-View 3D Reconstruction Networks Learn?
URI https://ieeexplore.ieee.org/document/8954121
WOSCitedRecordID wos000529484003059&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/eLvHCXMwlV1JS0MxEB5q8eDJpRV3cvBobN7LfvLQWjxIKS6lt_KyQUFasVX_vkneo_XgxVsICSEThsmXzPcNwHUhAvEmGCwqrTATxON4y-BYB2tLUTErdSYKP8rRSE2netyCmw0Xxnufk8_8bWrmv3y3tJ_pqaynNGdFYo3vSClrrtbmPYVGJCO0atR7CqJ7_cn4KeVuJUHKTCz6VT4lR4_h_v_WPYDuloaHxpsAcwgtvziC_ebeiBqvXHWAJ_1tNFii5zjszePJ3H8jOkAJWm4FYtGozvheoaypeteF1-H9S_8BN-UQ8LwkdI2ZMtRpSzmzztCiSshN00BLp7hxNKhSWk-qwKTjlWGKE0OMpq60qgwsOtoxtBfLhT8BxEOIMMUrG6fE6CS11TYVfonYQnhh1Cl0khVm77XixawxwNnf3eewl8xcJ1BdQDvuy1_Crv1az1cfV_mYfgD-FpKX
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NTwMhEJ001URPVVvjtxw8imUX2IWTh9amxrpptDa9NQsLSZOmNbbq3xfYTevBizdCIIQhk-HBvDcAN1FiiVFW4SSXArOEGOxuGRxLq3Wc5EynMhCFB2mWiclEDmtwu-HCGGNC8pm5883wl18s9ad_KmsLyVnkWeM7nLE4KtlamxcV6rBMIkWl3xMR2e6Mhy8-e8tLUgZq0a8CKiF-9Br_W_kAWlsiHhpuQswh1MziCBrVzRFVfrlqAvcK3Ki7RK9u2Nzg8cx8I9pFHlxuJWJRVuZ8r1BQVb1vwVvvYdTp46ogAp7FhK4xE4oWUlPOdKFolHvsJqmlcSG4KqgVcaoNyS1LC54rJjhRRElaxFrEljlXO4b6YrkwJ4C4tQ6oGKHdFBefUqml9qVfHLpITKLEKTS9FabvpebFtDLA2d_d17DXHz0PpoPH7Okc9r3Jy3SqC6i7PZpL2NVf69nq4yoc2Q_R0ZXe
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=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=What+Do+Single-View+3D+Reconstruction+Networks+Learn%3F&rft.au=Tatarchenko%2C+Maxim&rft.au=Richter%2C+Stephan+R.&rft.au=Ranftl%2C+Rene&rft.au=Li%2C+Zhuwen&rft.date=2019-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=3400&rft.epage=3409&rft_id=info:doi/10.1109%2FCVPR.2019.00352&rft.externalDocID=8954121