10 citations · 15 across the 9 of their papers we have counts for
9 papers · 1 filter
Deep Event Visual Odometry
Simon Klenk, Marvin Motzet, Lukas Koestler +1
Event cameras offer the exciting possibility of tracking the camera's pose during high-speed motion and in adverse lighting conditions. Despite this promise, existing event-based m…
Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares
Dominik Muhle, Lukas Koestler, Krishna Murthy Jatavallabhula +1
We propose a differentiable nonlinear least squares framework to account for uncertainty in relative pose estimation from feature correspondences. Specifically, we introduce a symm…
Masked Event Modeling: Self-Supervised Pretraining for Event Cameras
Simon Klenk, David Bonello, Lukas Koestler +2
Event cameras asynchronously capture brightness changes with low latency, high temporal resolution, and high dynamic range. However, annotation of event data is a costly and labori…
E-NeRF: Neural Radiance Fields from a Moving Event Camera
Simon Klenk, Lukas Koestler, Davide Scaramuzza +1
Estimating neural radiance fields (NeRFs) from "ideal" images has been extensively studied in the computer vision community. Most approaches assume optimal illumination and slow ca…
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…
Neural Implicit Representations for Physical Parameter Inference from a Single Video
Florian Hofherr, Lukas Koestler, Florian Bernard +1
Neural networks have recently been used to analyze diverse physical systems and to identify the underlying dynamics. While existing methods achieve impressive results, they are lim…
Intrinsic Neural Fields: Learning Functions on Manifolds
Lukas Koestler, Daniel Grittner, Michael Moeller +2
Neural fields have gained significant attention in the computer vision community due to their excellent performance in novel view synthesis, geometry reconstruction, and generative…
TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo
Lukas Koestler, Nan Yang, Niclas Zeller +1
In this paper, we present TANDEM a real-time monocular tracking and dense mapping framework. For pose estimation, TANDEM performs photometric bundle adjustment based on a sliding w…
Learning Monocular 3D Vehicle Detection without 3D Bounding Box Labels
L. Koestler, N. Yang, R. Wang +1
The training of deep-learning-based 3D object detectors requires large datasets with 3D bounding box labels for supervision that have to be generated by hand-labeling. We propose a…