Revealing Scenes by Inverting Structure From Motion Reconstructions

Many 3D vision systems localize cameras within a scene using 3D point clouds. Such point clouds are often obtained using structure from motion (SfM), after which the images are discarded to preserve privacy. In this paper, we show, for the first time, that such point clouds retain enough information...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 145 - 154
Hlavní autori: Pittaluga, Francesco, Koppal, Sanjeev J., Kang, Sing Bing, Sinha, Sudipta N.
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.06.2019
Predmet:
ISSN:1063-6919
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Many 3D vision systems localize cameras within a scene using 3D point clouds. Such point clouds are often obtained using structure from motion (SfM), after which the images are discarded to preserve privacy. In this paper, we show, for the first time, that such point clouds retain enough information to reveal scene appearance and compromise privacy. We present a privacy attack that reconstructs color images of the scene from the point cloud. Our method is based on a cascaded U-Net that takes as input, a 2D multichannel image of the points rendered from a specific viewpoint containing point depth and optionally color and SIFT descriptors and outputs a color image of the scene from that viewpoint. Unlike previous feature inversion methods, we deal with highly sparse and irregular 2D point distributions and inputs where many point attributes are missing, namely keypoint orientation and scale, the descriptor image source and the 3D point visibility. We evaluate our attack algorithm on public datasets and analyze the significance of the point cloud attributes. Finally, we show that novel views can also be generated thereby enabling compelling virtual tours of the underlying scene.
AbstractList Many 3D vision systems localize cameras within a scene using 3D point clouds. Such point clouds are often obtained using structure from motion (SfM), after which the images are discarded to preserve privacy. In this paper, we show, for the first time, that such point clouds retain enough information to reveal scene appearance and compromise privacy. We present a privacy attack that reconstructs color images of the scene from the point cloud. Our method is based on a cascaded U-Net that takes as input, a 2D multichannel image of the points rendered from a specific viewpoint containing point depth and optionally color and SIFT descriptors and outputs a color image of the scene from that viewpoint. Unlike previous feature inversion methods, we deal with highly sparse and irregular 2D point distributions and inputs where many point attributes are missing, namely keypoint orientation and scale, the descriptor image source and the 3D point visibility. We evaluate our attack algorithm on public datasets and analyze the significance of the point cloud attributes. Finally, we show that novel views can also be generated thereby enabling compelling virtual tours of the underlying scene.
Author Pittaluga, Francesco
Sinha, Sudipta N.
Kang, Sing Bing
Koppal, Sanjeev J.
Author_xml – sequence: 1
  givenname: Francesco
  surname: Pittaluga
  fullname: Pittaluga, Francesco
  organization: Univ. of Florida
– sequence: 2
  givenname: Sanjeev J.
  surname: Koppal
  fullname: Koppal, Sanjeev J.
  organization: Univ. of Florida
– sequence: 3
  givenname: Sing Bing
  surname: Kang
  fullname: Kang, Sing Bing
  organization: Microsoft Research
– sequence: 4
  givenname: Sudipta N.
  surname: Sinha
  fullname: Sinha, Sudipta N.
  organization: Microsoft Research
BookMark eNotjMtOwzAURA0CiVKyZsHGP5Di69v4sUQRLZWKQOGxrRz7GgW1DkrSSv17osJqNHOO5ppdpDYRY7cgZgDC3pefr9VMCrAzIYTEM5ZZbUBLAygtmnM2AaEwVxbsFcv6_nvUUAIoayasrOhAbtukL_7mKVHP6yNfpQN1w2kbur0f9h3xRdfu-HM7NG3iFfk29Sc01v6GXUa37Sn7zyn7WDy-l0_5-mW5Kh_WeSMFDjmFIKwOdRHRixBtAE_kwGgb5gpUJDf30khfSxWKSDo6jMJToBhGHRCn7O7vtyGizU_X7Fx33BhboNaIv8WtTyg
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2019.00023
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 9781728132938
1728132932
EISSN 1063-6919
EndPage 154
ExternalDocumentID 8953773
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-edd097db5f3c0df9d1ceea1879d4616fea4c282cb26d5fe7fa3f0cedefd0df133
IEDL.DBID RIE
ISICitedReferencesCount 85
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000529484000015&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 07:44:55 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-edd097db5f3c0df9d1ceea1879d4616fea4c282cb26d5fe7fa3f0cedefd0df133
PageCount 10
ParticipantIDs ieee_primary_8953773
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 2.5124576
Snippet Many 3D vision systems localize cameras within a scene using 3D point clouds. Such point clouds are often obtained using structure from motion (SfM), after...
SourceID ieee
SourceType Publisher
StartPage 145
SubjectTerms 3D from Multiview and Sensors
Cameras
Color
Data privacy
Deep Learning ; Image and Video Synthesis
Image reconstruction
Point cloud compression
Privacy
Security
Solid modeling
Structure from motion
Three-dimensional displays
Title Revealing Scenes by Inverting Structure From Motion Reconstructions
URI https://ieeexplore.ieee.org/document/8953773
WOSCitedRecordID wos000529484000015&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/eLvHCXMwlV1LSwMxEB7a4sFT1VZ8k4NH12Z3NsnuuVg8aClFpbeySSbQg630Bf57k3RpPXjxFoZAkgl5fMnM9wHcO4NOi0wnqNEleWZ0UoncQ5VUo1RoUqSoWvKihsNiMilHDXjY58IQUQw-o8dQjH_5dmE24amsV5QClcImNJWSu1yt_XsKeiQjy6Jm70l52et_jMYhdisQUvIgR_RLPiWeHoP2_9o9ge4hDY-N9gfMKTRofgbt-t7I6lW56kB_TFt_3_N1vDHsXUx_s0CgERgCvC1SxG6WxAbLxSd7jbo9LODOA3vsqgvvg6e3_nNSiyMks4zjOiFreamsFg4Nt660qe9NFbTDbS5T6ajKjYdTRmfSCkfKVei4IUvO-uoemZ5Da76Y0wUwdFL7qTIF1x4c2SBERh6lWeTOlVKIS-gEn0y_dvwX09odV3-br-E4OH0XTnUDLT8QuoUjs13PVsu7OGk_1OWbTg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEJ4gmugJFYxve_DoSne77W7PRIIRCCFouJFtO004CIZX4r-3LRvw4MVbM2nSx6SPr535PoBHq5lVPFERU8xGaaJVVPDUQZVYMZExHTMMqiXdrN_Px2M5qMDTLhcGEUPwGT77YvjLN3O99k9lzVxylmXsAA69claZrbV7UWEOywiZl_w9MZXN1sdg6KO3PCUl9YJEvwRUwvnRrv2v5VNo7BPxyGB3xJxBBWfnUCtvjqRcl8s6tIa4cTc-V8cZ_e5F1DfxFBqeI8DZAknseoGkvZh_kl5Q7iEeee75Y5cNeG-_jFqdqJRHiKYJZasIjaEyM4pbpqmx0sSuN4VXDzepiIXFItUOUGmVCMMtZrZglmo0aI2r7rDpBVRn8xleAmFWKOcsnVPl4JHxUmTocJph1FopOL-Cup-TydeWAWNSTsf13-YHOO6Met1J97X_dgMn3gHb4KpbqLpB4R0c6c1qulzcBwf-ABmmnpc
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=Revealing+Scenes+by+Inverting+Structure+From+Motion+Reconstructions&rft.au=Pittaluga%2C+Francesco&rft.au=Koppal%2C+Sanjeev+J.&rft.au=Kang%2C+Sing+Bing&rft.au=Sinha%2C+Sudipta+N.&rft.date=2019-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=145&rft.epage=154&rft_id=info:doi/10.1109%2FCVPR.2019.00023&rft.externalDocID=8953773