NAVER LABS Europe

IPIU workshop on Vision-based localization

13th February 2019 

Martin Humenberger will give a talk: "Modern approaches of visual localization". 
Abstract: Visual localization refers to estimating the 6DOF camera pose within a given 3D scene model using images. In this talk I will first present a quick overview about different methods, and second, I will detail more recent approaches which utilise deep learning techniques for visual localization. Traditional methods use descriptor matching between the query image and the 3D scene model as basis for pose computation, while modern learning-based approaches try to directly regress the pose or intermediate results of the localization pipeline. Furthermore, I will introduce a new synthetic dataset which explicitly targets challenging situations such as lighting changes and occlusions.

Martin Humenberger: Visual Localization Tutorial @ IPIU 2019 in Jeju ​