Direkt zum Inhalt springen
Computer Vision Group
TUM School of Computation, Information and Technology
Technical University of Munich

Technical University of Munich



Monocular Visual Odometry Dataset

We present a dataset for evaluating the tracking accuracy of monocular Visual Odometry (VO) and SLAM methods. It contains 50 real-world sequences comprising over 100 minutes of video, recorded across different environments – ranging from narrow indoor corridors to wide outdoor scenes.

All sequences contain mostly exploring camera motion, starting and ending at the same position: this allows to evaluate tracking accuracy via the accumulated drift from start to end, without requiring ground-truth for the full sequence.

In contrast to existing datasets, all sequences are photometrically calibrated: We provide the exposure times for each frame as reported by the sensor, the camera response function and the lens attenuation factors (vignetting). Further, we propose a simple approach to non-parametric vignette and camera response calibration, which require minimal set-up and are easy to reproduce.

Dataset Download

  • Individual sequences:

Sequence name Number of frames Duration FPS Min exposure Max exposure Download Preview Video Preview Video Rectified
sequence_01 4757 95.13s 50.02 1.66ms 19.98ms zip (1.30GB) play (5x) play (5x)
sequence_02 3500 69.98s 50.01 2.64ms 19.98ms zip (0.88GB) play (5x) play (5x)
sequence_03 5427 108.55s 50.00 0.24ms 13.93ms zip (1.51GB) play (5x) play (5x)
sequence_04 6921 138.47s 50.00 1.01ms 19.98ms zip (1.83GB) play (5x) play (5x)
sequence_05 6300 125.97s 50.01 0.11ms 19.98ms zip (2.01GB) play (5x) play (5x)
sequence_06 4500 90.04s 50.01 2.81ms 19.98ms zip (1.21GB) play (5x) play (5x)
sequence_07 3556 71.10s 50.01 0.87ms 7.45ms zip (0.94GB) play (5x) play (5x)
sequence_08 4300 86.08s 50.01 1.09ms 19.98ms zip (1.01GB) play (5x) play (5x)
sequence_09 2300 46.00s 50.04 5.03ms 15.03ms zip (0.38GB) play (5x) play (5x)
sequence_10 2100 41.98s 50.01 4.76ms 17.09ms zip (0.36GB) play (5x) play (5x)
sequence_11 1500 59.95s 25.00 0.58ms 17.47ms zip (0.25GB) play (5x) play (5x)
sequence_12 2250 89.99s 24.99 0.14ms 16.28ms zip (0.38GB) play (5x) play (5x)
sequence_13 1800 71.98s 24.99 0.47ms 32.13ms zip (0.28GB) play (5x) play (5x)
sequence_14 1550 61.93s 25.02 3.86ms 39.94ms zip (0.23GB) play (5x) play (5x)
sequence_15 2700 107.91s 25.01 0.32ms 32.27ms zip (0.50GB) play (5x) play (5x)
sequence_16 1850 73.93s 25.01 4.95ms 23.50ms zip (0.30GB) play (5x) play (5x)
sequence_17 4980 124.39s 40.03 0.34ms 2.37ms zip (0.99GB) play (5x) play (5x)
sequence_18 6200 154.94s 40.01 0.68ms 4.30ms zip (1.12GB) play (5x) play (5x)
sequence_19 8380 209.43s 40.00 0.09ms 1.00ms zip (1.65GB) play (5x) play (5x)
sequence_20 5380 134.45s 40.00 0.11ms 12.96ms zip (1.10GB) play (5x) play (5x)
sequence_21 5470 273.68s 20.00 0.05ms 1.89ms zip (1.47GB) play (5x) play (5x)
sequence_22 6340 316.98s 20.00 0.06ms 0.28ms zip (1.79GB) play (5x) play (5x)
sequence_23 3740 124.64s 29.99 0.42ms 3.17ms zip (0.89GB) play (5x) play (5x)
sequence_24 3500 116.64s 29.99 0.45ms 3.83ms zip (0.77GB) play (5x) play (5x)
sequence_25 4090 136.31s 29.99 0.41ms 3.87ms zip (0.96GB) play (5x) play (5x)
sequence_26 2760 91.95s 30.01 6.35ms 33.31ms zip (0.36GB) play (5x) play (5x)
sequence_27 3480 115.98s 30.02 0.03ms 0.16ms zip (0.69GB) play (5x) play (5x)
sequence_28 5550 185.31s 30.01 0.37ms 33.29ms zip (0.70GB) play (5x) play (5x)
sequence_29 8400 280.03s 30.02 0.01ms 0.69ms zip (2.30GB) play (5x) play (5x)
sequence_30 1800 85.30s 21.09 0.01ms 0.21ms zip (0.45GB) play (5x) play (5x)
sequence_31 3240 153.59s 21.09 0.01ms 0.26ms zip (0.85GB) play (5x) play (5x)
sequence_32 2700 127.99s 21.09 0.01ms 0.26ms zip (0.72GB) play (5x) play (5x)
sequence_33 2760 91.92s 30.01 0.02ms 0.43ms zip (0.68GB) play (5x) play (5x)
sequence_34 4290 203.38s 21.09 0.02ms 0.76ms zip (1.12GB) play (5x) play (5x)
sequence_35 2550 85.06s 30.00 5.47ms 33.31ms zip (0.36GB) play (5x) play (5x)
sequence_36 2350 78.29s 30.00 6.01ms 33.31ms zip (0.32GB) play (5x) play (5x)
sequence_37 2970 98.96s 30.00 3.63ms 33.31ms zip (0.38GB) play (5x) play (5x)
sequence_38 3330 133.17s 25.00 1.19ms 10.95ms zip (0.37GB) play (5x) play (5x)
sequence_39 3540 141.65s 24.99 1.52ms 14.56ms zip (0.38GB) play (5x) play (5x)
sequence_40 4350 174.42s 25.00 1.22ms 13.05ms zip (0.44GB) play (5x) play (5x)
sequence_41 3100 123.98s 24.99 5.34ms 25.52ms zip (0.42GB) play (5x) play (5x)
sequence_42 4830 224.49s 21.53 0.02ms 10.59ms zip (1.14GB) play (5x) play (5x)
sequence_43 2160 100.28s 21.53 0.05ms 1.12ms zip (0.66GB) play (5x) play (5x)
sequence_44 2100 97.50s 21.53 0.03ms 15.00ms zip (0.45GB) play (5x) play (5x)
sequence_45 3000 99.99s 29.99 0.14ms 0.66ms zip (0.93GB) play (5x) play (5x)
sequence_46 4110 137.07s 29.99 0.08ms 2.08ms zip (1.02GB) play (5x) play (5x)
sequence_47 3260 129.84s 25.13 0.35ms 4.26ms zip (0.99GB) play (5x) play (5x)
sequence_48 3250 129.41s 25.13 0.36ms 4.74ms zip (0.96GB) play (5x) play (5x)
sequence_49 3255 129.48s 25.13 0.21ms 1.78ms zip (0.82GB) play (5x) play (5x)
sequence_50 4050 161.12s 25.13 0.27ms 1.65ms zip (1.12GB) play (5x) play (5x)

Calibration sequences

  • All calibration sequences zip (13GB)
  • Individual sequences:

Sequence name Download Preview Video
narrowGamma_scene1 zip (2.02GB) play (5x)
narrowGamma_scene2 zip (1.20GB) play (5x)
narrowGamma_sweep1 zip (0.37GB) play (5x)
narrowGamma_sweep2 zip (0.76GB) play (5x)
narrowGamma_sweep3 zip (0.29GB) play (5x)
narrowGamma_vignette zip (0.35GB) play (5x)
narrow_checkerboard1 zip (0.27GB) play (5x)
narrow_checkerboard2 zip (0.05GB)
narrow_sweep1 zip (0.51GB) play (5x)
narrow_sweep2 zip (0.40GB) play (5x)
narrow_sweep3 zip (0.20GB) play (5x)
narrow_vignette zip (0.32GB) play (5x)
narrow_whitePaper zip (0.04GB) play (5x)
wideGamma_scene1 zip (1.56GB) play (5x)
wideGamma_sweep1 zip (0.53GB) play (5x)
wideGamma_sweep2 zip (0.70GB) play (5x)
wideGamma_vignette zip (0.41GB) play (5x)
wideGamma_vignette2 zip (0.42GB) play (5x)
wide_checkerboard1 zip (0.24GB) play (5x)
wide_checkerboard2 zip (0.04GB)
wide_sweep1 zip (0.46GB) play (5x)
wide_sweep2 zip (0.59GB) play (5x)
wide_vignette zip (0.55GB) play (5x)
wide_vignette2 zip (0.27GB) play (5x)
wide_whitePaper zip (0.06GB) play (5x)


Unless stated otherwise, all data in the Monocular Visual Odometry Dataset is licensed under a Creative Commons 4.0 Attribution License (CC BY 4.0) and the accompanying source code is licensed under a BSD-2-Clause License.


Export as PDF, XML, TEX or BIB

Journal Articles
[]DM-VIO: Delayed Marginalization Visual-Inertial Odometry (L. von Stumberg and D. Cremers), In IEEE Robotics and Automation Letters (RA-L) & International Conference on Robotics and Automation (ICRA), volume 7, 2022. ([arXiv][video][project page][supplementary][code]) [bibtex] [doi]
[]Omnidirectional DSO: Direct Sparse Odometry with Fisheye Cameras (H. Matsuki, L. von Stumberg, V. Usenko, J. Stueckler and D. Cremers), In IEEE Robotics and Automation Letters & Int. Conference on Intelligent Robots and Systems (IROS), IEEE, 2018. ([arxiv]) [bibtex] [pdf]
[]Online Photometric Calibration of Auto Exposure Video for Realtime Visual Odometry and SLAM (P. Bergmann, R. Wang and D. Cremers), In IEEE Robotics and Automation Letters (RA-L), volume 3, 2018. (This paper was also selected by ICRA'18 for presentation at the conference.[arxiv][video][code][project]) [bibtex] [pdf]ICRA'18 Best Vision Paper Award - Finalist
[]Direct Sparse Odometry (J. Engel, V. Koltun and D. Cremers), In IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018.  [bibtex] [pdf]
Conference and Workshop Papers
[]Tight Integration of Feature-based Relocalization in Monocular Direct Visual Odometry (M Gladkova, R Wang, N Zeller and D Cremers), In Proc. of the IEEE International Conference on Robotics and Automation (ICRA), 2021. ([project page]) [bibtex] [arXiv:2102.01191]
[]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] [arXiv:2003.01060] [pdf]Oral Presentation
[]Rolling-Shutter Modelling for Visual-Inertial Odometry (D. Schubert, N. Demmel, L. von Stumberg, V. Usenko and D. Cremers), In International Conference on Intelligent Robots and Systems (IROS), 2019. ([arxiv]) [bibtex] [pdf]
[]Direct Sparse Odometry With Rolling Shutter (D. Schubert, N. Demmel, V. Usenko, J. Stueckler and D. Cremers), In European Conference on Computer Vision (ECCV), 2018. ([supplementary][arxiv]) [bibtex] [pdf]Oral Presentation
[]Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry (N. Yang, R. Wang, J. Stueckler and D. Cremers), In European Conference on Computer Vision (ECCV), 2018. ([arxiv],[supplementary],[project]) [bibtex]Oral Presentation
[]LDSO: Direct Sparse Odometry with Loop Closure (X. Gao, R. Wang, N. Demmel and D. Cremers), In International Conference on Intelligent Robots and Systems (IROS), 2018. ([arxiv][video][code][project]) [bibtex]
[]Direct Sparse Visual-Inertial Odometry using Dynamic Marginalization (L. von Stumberg, V. Usenko and D. Cremers), In International Conference on Robotics and Automation (ICRA), 2018. ([supplementary][video][arxiv]) [bibtex] [pdf]
[]Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras (R. Wang, M. Schwörer and D. Cremers), In International Conference on Computer Vision (ICCV), 2017. ([supplementary][video][arxiv][project]) [bibtex] [pdf]
[]Direct Sparse Odometry (J. Engel, V. Koltun and D. Cremers), In arXiv:1607.02565, 2016.  [bibtex] [pdf]
[]A Photometrically Calibrated Benchmark For Monocular Visual Odometry (J. Engel, V. Usenko and D. Cremers), In arXiv:1607.02555, 2016.  [bibtex] [pdf]
Powered by bibtexbrowser
Export as PDF, XML, TEX or BIB

Rechte Seite

Informatik IX
Computer Vision Group

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

Follow us on:



CVPR 2023

We have six papers accepted to CVPR 2023.


NeurIPS 2022

We have two papers accepted to NeurIPS 2022.


WACV 2023

We have two papers accepted at WACV 2023.


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.