Digging Into Self-Supervised Learning of Feature Descriptors

Iaroslav Melekhov, Zakaria Laskar, Xiaotian Li, Shuzhe Wang, Juho Kannala

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

Abstrakti

Fully-supervised CNN-based approaches for learning local image descriptors have shown remarkable results in a wide range of geometric tasks. However, most of them require per-pixel ground-truth keypoint correspondence data which is difficult to acquire at scale. To address this challenge, recent weakly-and self-supervised methods can learn feature descriptors from relative camera poses or using only synthetic rigid transformations such as homographies. In this work, we focus on understanding the limitations of existing self-supervised approaches and propose a set of improvements that combined lead to powerful feature descriptors. We show that increasing the search space from in-pair to in-batch for hard negative mining brings consistent improvement. To enhance the discriminativeness of feature descriptors, we propose a coarse-to-fine method for mining local hard negatives from a wider search space by using global visual image descriptors. We demonstrate that a combination of synthetic homography transformation, color augmentation, and photorealistic image stylization produces useful representations that are viewpoint and illumination invariant. The feature descriptors learned by the proposed approach perform competitively and surpass their fully- and weakly-supervised counterparts on various geometric benchmarks such as image-based localization, sparse feature matching, and image retrieval.
AlkuperäiskieliEnglanti
OtsikkoProceedings - 2021 International Conference on 3D Vision, 3DV 2021
KustantajaIEEE
Sivut1144-1155
Sivumäärä12
ISBN (elektroninen)978-1-6654-2688-6
ISBN (painettu)978-1-6654-2689-3
DOI - pysyväislinkit
TilaJulkaistu - tammikuuta 2022
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaInternational Conference on 3D Vision - Virtual, Online, Iso-Britannia
Kesto: 1 joulukuuta 20213 joulukuuta 2021
Konferenssinumero: 9
https://3dv2021.surrey.ac.uk/

Conference

ConferenceInternational Conference on 3D Vision
Lyhennettä3DV
Maa/AlueIso-Britannia
KaupunkiVirtual, Online
Ajanjakso01/12/202103/12/2021
www-osoite

Sormenjälki

Sukella tutkimusaiheisiin 'Digging Into Self-Supervised Learning of Feature Descriptors'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä