TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

DGC-Net: Dense geometric correspondence network

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019
KustantajaIEEE
Sivut1034-1042
Sivumäärä9
ISBN (elektroninen)9781728119755
DOI - pysyväislinkit
TilaJulkaistu - 4 maaliskuuta 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE Winter Conference on Applications of Computer Vision - Waikoloa Village, Yhdysvallat
Kesto: 7 tammikuuta 201911 tammikuuta 2019

Julkaisusarja

NimiIEEE Winter Conference on Applications of Computer Vision
ISSN (painettu)1550-5790

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision
MaaYhdysvallat
KaupunkiWaikoloa Village
Ajanjakso7/01/1911/01/19

Tiivistelmä

This paper addresses the challenge of dense pixel correspondence estimation between two images. This problem is closely related to optical flow estimation task where Con-vNets (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.