SegLoc: Learning Segmentation-Based Representations for Privacy-Preserving Visual Localization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00372022" target="_blank" >RIV/68407700:21230/23:00372022 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/23:00372022

Výsledek na webu

<a href="https://doi.org/10.1109/CVPR52729.2023.01476" target="_blank" >https://doi.org/10.1109/CVPR52729.2023.01476</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR52729.2023.01476" target="_blank" >10.1109/CVPR52729.2023.01476</a>

Jazyk výsledku

angličtina

Název v původním jazyce

SegLoc: Learning Segmentation-Based Representations for Privacy-Preserving Visual Localization

Popis výsledku v původním jazyce

Inspired by properties of semantic segmentation, in this paper we investigate how to leverage robust image segmentation in the context of privacy-preserving visual localization. We propose a new localization framework, SegLoc, that leverages image segmentation to create robust, compact, and privacy-preserving scene representations, i.e., 3D maps. We build upon the correspondence-supervised, fine-grained segmentation approach from [42], making it more robust by learning a set of cluster labels with discriminative clustering, additional consistency regularization terms and we jointly learn a global image representation along with a dense local representation. In our localization pipeline, the former will be used for retrieving the most similar images, the latter to refine the retrieved poses by minimizing the label inconsistency between the 3D points of the map and their projection onto the query image. In various experiments, we show that our proposed representation allows to achieve (close-to) state-of-the-art pose estimation results while only using a compact 3D map that does not contain enough information about the original images for an attacker to reconstruct personal information.

Název v anglickém jazyce

SegLoc: Learning Segmentation-Based Representations for Privacy-Preserving Visual Localization

Popis výsledku anglicky

Inspired by properties of semantic segmentation, in this paper we investigate how to leverage robust image segmentation in the context of privacy-preserving visual localization. We propose a new localization framework, SegLoc, that leverages image segmentation to create robust, compact, and privacy-preserving scene representations, i.e., 3D maps. We build upon the correspondence-supervised, fine-grained segmentation approach from [42], making it more robust by learning a set of cluster labels with discriminative clustering, additional consistency regularization terms and we jointly learn a global image representation along with a dense local representation. In our localization pipeline, the former will be used for retrieving the most similar images, the latter to refine the retrieved poses by minimizing the label inconsistency between the 3D points of the map and their projection onto the query image. In various experiments, we show that our proposed representation allows to achieve (close-to) state-of-the-art pose estimation results while only using a compact 3D map that does not contain enough information about the original images for an attacker to reconstruct personal information.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

ISBN

979-8-3503-0129-8

ISSN

1063-6919

e-ISSN

2575-7075

Počet stran výsledku

12

Strana od-do

15380-15391

Název nakladatele

IEEE Computer Society

Místo vydání

USA

Místo konání akce

Vancouver

Datum konání akce

18. 6. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001062522107067