Relative Camera Pose Estimation Using Convolutional Neural Networks

Iaroslav Melekhov, Juha Ylioinas, Juho Kannala, Esa Rahtu

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

47 Citations (Scopus)


This paper presents a convolutional neural network based approach for estimating the relative pose between two cameras. The proposed network takes RGB images from both cameras as input and directly produces the relative rotation and translation as output. The system is trained in an end-to-end manner utilising transfer learning from a large scale classification dataset. The introduced approach is compared with widely used local feature based methods (SURF, ORB) and the results indicate a clear improvement over the baseline. In addition, a variant of the proposed architecture containing a spatial pyramid pooling (SPP) layer is evaluated and shown to further improve the performance.
Original languageEnglish
Title of host publicationAdvanced Concepts for Intelligent Vision Systems
Subtitle of host publication18th International Conference, ACIVS 2017, Antwerp, Belgium, September 18-21, 2017, Proceedings
EditorsJacques Blanc-Talon, Rudi Penne, Wilfried Philips, Dan Popescu, Paul Scheunders
Place of PublicationCham
Number of pages13
ISBN (Electronic)978-3-319-70353-4
Publication statusPublished - 2017
MoE publication typeA4 Article in a conference publication
EventInternational Conference on Advanced Concepts for Intelligent Vision Systems - Antwerp, Belgium
Duration: 18 Sep 201721 Sep 2017
Conference number: 18

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceInternational Conference on Advanced Concepts for Intelligent Vision Systems
Abbreviated titleACIVS

Fingerprint Dive into the research topics of 'Relative Camera Pose Estimation Using Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this