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

Technical University of Munich



Submission form for automatic evaluation of RGB-D SLAM results

Groundtruth trajectory
Estimated trajectory
Evaluation options Offset: seconds (add to stamps of estimated traj.)
Scale: (scale estimated traj. by this factor)
Evaluation mode absolute trajectory error (recommended for the evaluation of visual SLAM methods)
relative pose error for pose pairs with a distance of (recommended for the evaluation of visual odometry methods)
relative pose error for all pairs (downsampled to pairs, alternative method for the evaluation of visual SLAM methods)

Runs the evaluation script on your data and displays the result. No data will be permanently saved on our servers. Alternatively, you can also download the evaluation script and perform the evaluation offline. Additional information about the evaluation options and the file formats is available. We also provide an example trajectory for freiburg1/xyz by RGBD-SLAM as well as instructions how to reproduce these trajectories.

Rechte Seite

Informatik IX
Computer Vision Group

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

Follow us on:



Fulbright PULSE podcast on Prof. Cremers went online on Apple Podcasts and Spotify.


MCML Kick-Off

On July 27th, we are organizing the Kick-Off of the Munich Center for Machine Learning in the Bavarian Academy of Sciences.


AI Symposium

On July 22nd 2022, we are organizing a Symposium on AI within the Technology Forum of the Bavarian Academy of Sciences.


We are organizing a workshop on Map-Based Localization for Autonomous Driving at ECCV 2022, Tel Aviv, Israel.


In April 2022 Jürgen Sturm and Daniel Cremers were featured among the top 6 most influential scholars in robotics of the last decade.