12 papers
DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment
Mariia Gladkova, Nikita Korobov, Nikolaus Demmel +3
Direct methods have shown excellent performance in the applications of visual odometry and SLAM. In this work we propose to leverage their effectiveness for the task of 3D multi-ob…
The Probabilistic Normal Epipolar Constraint for Frame-To-Frame Rotation Optimization under Uncertain Feature Positions
Dominik Muhle, Lukas Koestler, Nikolaus Demmel +2
The estimation of the relative pose of two camera views is a fundamental problem in computer vision. Kneip et al. proposed to solve this problem by introducing the normal epipolar…
Multidirectional Conjugate Gradients for Scalable Bundle Adjustment
Simon Weber, Nikolaus Demmel, Daniel Cremers
We revisit the problem of large-scale bundle adjustment and propose a technique called Multidirectional Conjugate Gradients that accelerates the solution of the normal equation by…
Towards Robust Monocular Visual Odometry for Flying Robots on Planetary Missions
Martin Wudenka, Marcus G. Müller, Nikolaus Demmel +4
In the future, extraterrestrial expeditions will not only be conducted by rovers but also by flying robots. The technical demonstration drone Ingenuity, that just landed on Mars, w…
TUM-VIE: The TUM Stereo Visual-Inertial Event Dataset
Simon Klenk, Jason Chui, Nikolaus Demmel +1
Event cameras are bio-inspired vision sensors which measure per pixel brightness changes. They offer numerous benefits over traditional, frame-based cameras, including low latency,…
Rolling-Shutter Modelling for Direct Visual-Inertial Odometry
David Schubert, Nikolaus Demmel, Lukas von Stumberg +2
We present a direct visual-inertial odometry (VIO) method which estimates the motion of the sensor setup and sparse 3D geometry of the environment based on measurements from a roll…