DGC-Net: Dense Geometric Correspondence Network

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

Researchers

Research units

  • University Hospital of Oulu
  • Swiss Federal Institute of Technology Zurich
  • Tampere University of Technology

Abstract

This paper addresses the challenge of dense pixel correspondence estimation between two images. This problem is closely related to optical flow estimation task where ConvNets (CNNs) have recently achieved significant progress. While optical flow methods produce very accurate results for the small pixel translation and limited appearance variation scenarios, they hardly deal with the strong geometric transformations that we consider in this work. In this paper, we propose a coarse-to-fine CNN-based framework that can leverage the advantages of optical flow approaches and extend them to the case of large transformations providing dense and subpixel accurate estimates. It is trained on synthetic transformations and demonstrates very good performance to unseen, realistic, data. Further, we apply our method to the problem of relative camera pose estimation and demonstrate that the model outperforms existing dense approaches.

Details

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019
Publication statusPublished - 4 Mar 2019
MoE publication typeA4 Article in a conference publication
EventIEEE Winter Conference on Applications of Computer Vision - Waikoloa Village, United States
Duration: 7 Jan 201911 Jan 2019
Conference number: 19

Publication series

NameIEEE Winter Conference on Applications of Computer Vision
PublisherIEEE
ISSN (Print)2472-6737

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision
Abbreviated titleWACV
CountryUnited States
CityWaikoloa Village
Period07/01/201911/01/2019

ID: 34750252