SConE: Siamese Constellation Embedding Descriptor for Image Matching
Tomasz Trzciński , Jacek Komorowski , Łukasz Dąbała , Konrad Czarnota , Grzegorz Kurzejamski , Simon Lynen
AbstractNumerous 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.
|Publication size in sheets||0.6|
|Book||Leal-Taixé Laura, Roth Stefan (eds.): Computer Vision – ECCV 2018 Workshops, Lecture Notes In Computer Science, vol. 11129, 2019, Springer International Publishing, ISBN 978-3-030-11020-8, [978-3-030-11021-5 (eBook)], 753 p.|
|Keywords in English||Feature descriptor Image matching Siamese networks|
|Score||= 15.0, 10-07-2019, ChapterFromConference|
|Publication indicators||= 0|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.