Taking a Deeper Look at the Inverse Compositional Algorithm

In this paper, we provide a modern synthesis of the classic inverse compositional algorithm for dense image alignment. We first discuss the assumptions made by this well-established technique, and subsequently propose to relax these assumptions by incorporating data-driven priors into this model. Mo...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 4576 - 4585
Main Authors: Lv, Zhaoyang, Dellaert, Frank, Rehg, James M., Geiger, Andreas
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2019
Subjects:
3D from Multiview and Sensors
Computer vision
Data models
Integrated circuits
Lighting
Motion and Tracking
Motion estimation
Neural networks
Optimization Methods
Three-dimensional displays
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract In this paper, we provide a modern synthesis of the classic inverse compositional algorithm for dense image alignment. We first discuss the assumptions made by this well-established technique, and subsequently propose to relax these assumptions by incorporating data-driven priors into this model. More specifically, we unroll a robust version of the inverse compositional algorithm and replace multiple components of this algorithm using more expressive models whose parameters we train in an end-to-end fashion from data. Our experiments on several challenging 3D rigid motion estimation tasks demonstrate the advantages of combining optimization with learning-based techniques, outperforming the classic inverse compositional algorithm as well as data-driven image-to-pose regression approaches.
AbstractList In this paper, we provide a modern synthesis of the classic inverse compositional algorithm for dense image alignment. We first discuss the assumptions made by this well-established technique, and subsequently propose to relax these assumptions by incorporating data-driven priors into this model. More specifically, we unroll a robust version of the inverse compositional algorithm and replace multiple components of this algorithm using more expressive models whose parameters we train in an end-to-end fashion from data. Our experiments on several challenging 3D rigid motion estimation tasks demonstrate the advantages of combining optimization with learning-based techniques, outperforming the classic inverse compositional algorithm as well as data-driven image-to-pose regression approaches.
Author Lv, Zhaoyang
Rehg, James M.
Geiger, Andreas
Dellaert, Frank
Author_xml – sequence: 1
  givenname: Zhaoyang
  surname: Lv
  fullname: Lv, Zhaoyang
  organization: GEORGIA TECH
– sequence: 2
  givenname: Frank
  surname: Dellaert
  fullname: Dellaert, Frank
  organization: Georgia Tech
– sequence: 3
  givenname: James M.
  surname: Rehg
  fullname: Rehg, James M.
  organization: Georgia Institute of Technology
– sequence: 4
  givenname: Andreas
  surname: Geiger
  fullname: Geiger, Andreas
  organization: MPI-IS and Univ. of Tuebingen
BookMark eNotzMtKw0AUgOFRFKw1axdu5gUSz5mZzAVXJd4KAUWq2zJJTtqxSaYkQfDtFXT1Lz74L9nZEAdi7BohQwR3W3y8vmUC0GUAyuAJS5yxaIRFKZy0p2yBoGWqHboLlkzTJwBIgaidXbC7jT-EYcc9vyc60sjLGA_cz3zeE18PXzROxIvYH-MU5hAH3_FVt4tjmPf9FTtvfTdR8t8le3982BTPafnytC5WZRoEyDltlHOVFjVWlVdkWzJGGee9J43SmlbVra2hhqapTO4UtrURngDqvJK_KOSS3fx9AxFtj2Po_fi9tS5XUlv5AxOkSgk
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2019.00471
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 4585
ExternalDocumentID 8954368
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-d499b62c1bba4e8fe77479aaae61387f4cf8c0c0ddb75941fc72ae00c5b3f4c23
IEDL.DBID RIE
ISICitedReferencesCount 40
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000529484004077&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 02:24:36 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-d499b62c1bba4e8fe77479aaae61387f4cf8c0c0ddb75941fc72ae00c5b3f4c23
PageCount 10
ParticipantIDs ieee_primary_8954368
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 2.3710182
Snippet In this paper, we provide a modern synthesis of the classic inverse compositional algorithm for dense image alignment. We first discuss the assumptions made by...
SourceID ieee
SourceType Publisher
StartPage 4576
SubjectTerms 3D from Multiview and Sensors
Computer vision
Data models
Integrated circuits
Lighting
Motion and Tracking
Motion estimation
Neural networks
Optimization Methods
Three-dimensional displays
Title Taking a Deeper Look at the Inverse Compositional Algorithm
URI https://ieeexplore.ieee.org/document/8954368
WOSCitedRecordID wos000529484004077&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/eLvHCXMwlV1LawIxEB5UeujJtlr6JoceuzX7TEJPxVZ6EJFixZvkMWkF68q69vc3WRe99NJDICQhgQnDzCTffANwn1GbSFQ2sBFikEgXoHCqwkA4U50qbUJTMd5Mh2w04rOZGDfgYZ8Lg4gV-Awffbf6yze53vqnsh4XqSdMb0KTsWyXq7V_T4ldJJMJXrP3hFT0-tPxu8dueULKpEqRP5RPqazHoP2_c0-ge0jDI-O9gTmFBq7OoF37jaTWyk0HniZVSSkiyQviGgsydJ4zkSVxzh3xRBrFBolX_BqgJZfkefmZF4vy67sLH4PXSf8tqIsiBIuIxmVgXIiiskiHSskEuUXnvzEhpURnmDmzibZcU02NUSwVSWg1iyRSqlMVu8koPofWKl_hBRBppTAy5ShCt5V2yyK0TqcjnaWxa5fQ8bKYr3e8F_NaDFd_D1_DsRf2DkZ1A62y2OItHOmfcrEp7qrL-gV-SJdK
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5qFfRUtRXf5uDRtdl3gieploprKVJLbyXJTrRQu2W79febbJf24sVDICQhgQnDzCTffANwG1EdCJTa0R6iEwgToDAqXYcbUx1KlbppyXgzSuJ-n43HfFCDu00uDCKW4DO8t93yLz_N1Mo-lbUZDy1h-g7s2spZVbbW5kXFN7FMxFnF3-NS3u6MBu8WvWUpKYMySX5bQKW0H93G_04-hNY2EY8MNibmCGo4P4ZG5TmSSi-XTXgYlkWliCBPiAvMSWJ8ZyIKYtw7Yqk08iUSq_oVREvMyOPsM8unxdd3Cz66z8NOz6nKIjhTj_qFk5ogRUaecqUUATKNxoOLuRACjWlmsQ6UZooqmqYyDnngahV7AilVofTNpOefQH2ezfEUiNCCpyJkyF2zlTLLPNRGqz0Vhb5pZ9C0spgs1swXk0oM538P38B-b_iWTJKX_usFHFjBr0FVl1Av8hVewZ76KabL_Lq8uF-QMpqT
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=Taking+a+Deeper+Look+at+the+Inverse+Compositional+Algorithm&rft.au=Lv%2C+Zhaoyang&rft.au=Dellaert%2C+Frank&rft.au=Rehg%2C+James+M.&rft.au=Geiger%2C+Andreas&rft.date=2019-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=4576&rft.epage=4585&rft_id=info:doi/10.1109%2FCVPR.2019.00471&rft.externalDocID=8954368