Event-camera localization using deep architectures
Join us for our upcoming Future Computing Seminar Series
Speaker: Prof. Friedrich Fraundorfer, Technische Universität Graz (TU Graz)
Date: Wednesday, August 19th, 2026, 11:00 CET
Where: ETZ F91
Abstract:
The talk will discuss map-based localization for event-cameras. In
particular the talk will discuss the case of pre-created maps of
different modalities, in particular Lidar-maps and maps created using
RGB cameras.
The first part of the talk will consider the case of localizing an
event-camera in a Lidar-map by calculating multi-modal optical flow
between depth-maps and event-frames.
The second talk will consider the case of localization using a Gaussian
splat created from an RGB camera by optimizing a cost function that
measures the alignment between a measured event frame and an event-framecreated by the Gaussian splat.
Speaker Bio:
Friedrich Fraundorfer is Full Professor at the Institute of Visual
Computing at Graz University of Technology (TUG). He received the Ph.D.
degree in computer science from TU Graz, Austria in 2006 working at the
Institute of Computer Graphics and Vision headed by Franz Leberl and
Horst Bischof. In 2006 he joined the group of David Nister at the
University of Kentucky as a post-doc researcher. He collaborated with
Henrik Stewenius and others on large scale image search and 3D computer
vision. In 2007 he joined the group of Marc Pollefeys at the University
of North Carolina at Chapel Hill as a post-doc researcher to work on
large scale 3D reconstructions collaborating with Jan-Michael Frahm, and
Changchang Wu. In 2007 the group moved to ETH Zurich, Switzerland, where
he had a lecturer position at the Computer Vision and Geometry Lab
headed by Marc Pollefeys. From 2012 to 2014 he acted as Deputy Director
of the Chair of Remote Sensing Technology at the Faculty of Civil, Geo
and Environmental Engineering at the Technische Universität München.
With his team he works in the research areas of 3D computer vision,
robot vision and machine learning with a special focus on computer
vision for robotics. He is the author of a well-received two-part
tutorial about visual odometry in the IEEE Robotics and Automation
Magazine. His work on autonomous UAVs got nominated for the Best Paper
Award at IEEE IROS 2012.