Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/12516
Title: Semantic pose verification for outdoor visual localization with self-supervised contrastive learning
Authors: Orhan, Semih
Guerrero, Jose J.
Baştanlar, Yalın
Keywords: Visual localization
Cameras
Semantic similarity
Query processing
Publisher: IEEE
Abstract: Any city-scale visual localization system has to overcome long-term appearance changes, such as varying illumination conditions or seasonal changes between query and database images. Since semantic content is more robust to such changes, we exploit semantic information to improve visual localization. In our scenario, the database consists of gnomonic views generated from panoramic images (e.g. Google Street View) and query images are collected with a standard field-of-view camera at a different time. To improve localization, we check the semantic similarity between query and database images, which is not trivial since the position and viewpoint of the cameras do not exactly match. To learn similarity, we propose training a CNN in a self-supervised fashion with contrastive learning on a dataset of semantically segmented images. With experiments we showed that this semantic similarity estimation approach works better than measuring the similarity at pixel-level. Finally, we used the semantic similarity scores to verify the retrievals obtained by a state-of-the-art visual localization method and observed that contrastive learning-based pose verification increases top-1 recall value to 0.90 which corresponds to a 2% improvement.
Description: This work was supported by the Scientific and Technological Research Council of Turkey under Grant No. 120E500 and also under 2214-A International Researcher Fellowship Programme.
URI: https://doi.org/10.1109/CVPRW56347.2022.00444
https://hdl.handle.net/11147/12516
Appears in Collections:Computer Engineering / Bilgisayar Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Files in This Item:
File Description SizeFormat 
Semantic_Pose.pdfConference Object3.67 MBAdobe PDFView/Open
Show full item record



CORE Recommender

WEB OF SCIENCETM
Citations

1
checked on Mar 27, 2024

Page view(s)

138
checked on Mar 25, 2024

Download(s)

54
checked on Mar 25, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.