Kunal Chelani, Electrical engineering

Kunal Chelani is a PhD student in the research group Computer vision, Division of Signal processing and Biomedical engineering

Discussion leader is Assoc. senior lecturer Viktor Larsson, Lund University

Examiner is Professor Fredrik Kahl, Division of Signal processing and Biomedical engineering

Abstract

Visual localization is the process of finding out the pose of a camera from which an image was taken and it is a central problem in several 3D computer vision tasks. With the increasing popularity of AR/VR/MR devices and cloud-based applications, the privacy of user content has become an essential factor to consider in designing clientserver-based visual localization pipelines. This document discusses the privacy threats that arise as information is shared between the client and a server during different stages of a typical cloud-based visual localization pipeline. Our own research is positioned with respect to the recent works in this domain.