Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich



Distributed Photometric Bundle Adjustment


In this paper we demonstrate that global photometric bundle adjustment (PBA) over all past keyframes can significantly improve the global accuracy of a monocular SLAM map compared to geometric techniques such as pose-graph optimization or traditional (geometric) bundle adjustment. However, PBA is computationally expensive in runtime, and memory usage can be prohibitively high. In order to address this scalability issue, we formulate PBA as an approximate consensus program. Due to its decomposable structure, the problem can be solved with block coordinate descent in parallel across multiple independent workers, each having lower requirements on memory and computational resources. For improved accuracy and convergence, we propose a novel gauge aware consensus update. Our experiments on real-world data show an average error reduction of 62% compared to odometry and 33% compared to intermediate pose-graph optimization, and that compared to the central optimization on a single machine, our distributed PBA achieves competitive pose-accuracy and cost.

Open-Source Code

Coming soon: The source code is still being prepared and documented and will be released shortly. Feel free to watch the repository to get a notification when it becomes available: https://github.com/tum-vision/dbatk


Export as PDF, XML, TEX or BIB

Conference and Workshop Papers
[]Distributed Photometric Bundle Adjustment (N Demmel, M Gao, E Laude, T Wu and D Cremers), In International Conference on 3D Vision (3DV), 2020. ([project page][code]) [bibtex] [pdf]Oral Presentation
Powered by bibtexbrowser
Export as PDF, XML, TEX or BIB

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching info@vision.in.tum.de

Follow us on:
CVG Group DVL Group



Thomas Pock (TU Graz) will give a talk in the TUM AI lecture series on April 15th, 3pm! Livestream


Max Welling (University of Amsterdam) will give a talk in the TUM AI lecture series on April 1st, 3pm! Livestream


We have seven papers (4 orals, 3 posters) accepted to CVPR 2021!


We have two papers accepted to ICRA 2021!


Maks Ovsjanikov (Ecole Polytechnique) will give a talk in the TUM AI lecture series on March 11th, 3pm! Livestream