SConE: Siamese Constellation Embedding Descriptor for Image Matching

Tomasz Trzciński , Jacek Komorowski , Łukasz Dąbała , Konrad Czarnota , Grzegorz Kurzejamski , Simon Lynen


Numerous computer vision applications rely on local feature descriptors, such as SIFT, SURF or FREAK, for image matching. Although their local character makes image matching processes more robust to occlusions, it often leads to geometrically inconsistent keypoint matches that need to be filtered out, e.g. using RANSAC. In this paper we propose a novel, more discriminative, descriptor that includes not only local feature representation, but also information about the geometric layout of neighbouring keypoints. To that end, we use a Siamese architecture that learns a low-dimensional feature embedding of keypoint constellation by maximizing the distances between non-corresponding pairs of matched image patches, while minimizing it for correct matches. The 48-dimensional floating point descriptor that we train is built on top of the state-of-the-art FREAK descriptor achieves significant performance improvement over the competitors on a challenging TUM dataset.
Author Tomasz Trzciński (FEIT / IN)
Tomasz Trzciński,,
- The Institute of Computer Science
, Jacek Komorowski (FEIT / ICS)
Jacek Komorowski,,
- The Institute of Computer Science
, Łukasz Dąbała (FEIT / IN)
Łukasz Dąbała,,
- The Institute of Computer Science
, Konrad Czarnota - [Warsaw University of Technology (PW)]
Konrad Czarnota,,
- Politechnika Warszawska
, Grzegorz Kurzejamski (FoEE / ICIE)
Grzegorz Kurzejamski,,
- The Institute of Control and Industrial Electronics
, Simon Lynen - [Google LLC]
Simon Lynen,,
Publication size in sheets0.6
Book Leal-Taixé Laura, Roth Stefan (eds.): Computer Vision – ECCV 2018 Workshops, Lecture Notes In Computer Science, vol. 11129, 2019, Springer, ISBN 978-3-030-11020-8, [978-3-030-11021-5 (eBook)], 753 p.
2019_Bookmatter_ComputerVisionECCV2018Workshop.pdf / No licence information (file archived - login or check accessibility on faculty)
Keywords in EnglishFeature descriptor Image matching Siamese networks
Languageen angielski
Score (nominal)140
Score sourceconferenceList
ScoreMinisterial score = 140.0, 02-02-2020, ChapterFromConference
Publication indicators Scopus Citations = 1
Citation count*
Share Share

Get link to the record

* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Are you sure?