D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry (bibtex)

by N. Yang, L. von Stumberg, R. Wang and D. Cremers

Reference:

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry (N. Yang, L. von Stumberg, R. Wang and D. Cremers), In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

Bibtex Entry:

@string{cvpr="IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"}
@inproceedings{yang20d3vo,
 author = {N. Yang and L. von Stumberg and R. Wang and D. Cremers},
 title = {D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year = {2020},
 eprint = {2003.01060},
 eprinttype = {arXiv},
 eprintclass = {cs.CV},
 award = {Oral Presentation},
 keywords = {dso,dvso, deep learning, monocular depth estimation, semi-supervised learning, slam, visual odometry,d3vo, vslam},
}

by N. Yang, L. von Stumberg, R. Wang and D. Cremers

Reference:

Bibtex Entry:

@string{cvpr="IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"}
@inproceedings{yang20d3vo,
 author = {N. Yang and L. von Stumberg and R. Wang and D. Cremers},
 title = {D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year = {2020},
 eprint = {2003.01060},
 eprinttype = {arXiv},
 eprintclass = {cs.CV},
 award = {Oral Presentation},
 keywords = {dso,dvso, deep learning, monocular depth estimation, semi-supervised learning, slam, visual odometry,d3vo, vslam},
}

Research Interests
Selected Projects

Lukas von Stumberg

PhD Student

Technical University of Munich

School of Computation, Information and Technology
Informatics 9
Boltzmannstrasse 3
85748 Garching
Germany

Fax: +49-89-289-17757
Office:
Mail: stumberg@in.tum.de

Find me on Google Scholar Linkedin

Research Interests

My research interests are visual and visual-inertial SLAM, robotics, and 3D reconstruction. I like to apply both traditional methods and deep learning.

Selected Projects

GN-Net: The Gauss-Newton Loss for Multi-Weather Relocalization

Using our novel Gauss-Newton loss we improve the robustness of direct methods against strong illumination changes and bad initializations. This allows us to accurately relocalize between different weathers. Project Page

VI-DSO: Direct Sparse Visual-Inertial Odometry using Dynamic Marginalization

In my Master thesis on direct visual-inertial odometry we demonstrate state-of-the-art performance on the EuRoC dataset. Project Page

From Monocular SLAM to Autonomous Drone Exploration

In my Bachelor thesis I have used LSD-SLAM to explore an unknown environment with an autonomous drone.

Table of Contents