DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras

Zachary Teed; Jia Deng

DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras

Zachary Teed, Jia Deng

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We introduce DROID-SLAM, a new deep learning based SLAM system. DROID-SLAM consists of recurrent iterative updates of camera pose and pixelwise depth through a Dense Bundle Adjustment layer. DROID-SLAM is accurate, achieving large improvements over prior work, and robust, suffering from substantially fewer catastrophic failures. Despite training on monocular video, it can leverage stereo or RGB-D video to achieve improved performance at test time. The URL to our open source code is https://github. com/princeton-vl/DROID-SLAM.

Original language	English (US)
Title of host publication	Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021
Editors	Marc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan
Publisher	Neural information processing systems foundation
Pages	16558-16569
Number of pages	12
ISBN (Electronic)	9781713845393
State	Published - 2021
Event	35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual, Online Duration: Dec 6 2021 → Dec 14 2021

Publication series

Name	Advances in Neural Information Processing Systems
Volume	20
ISSN (Print)	1049-5258

Conference

Conference	35th Conference on Neural Information Processing Systems, NeurIPS 2021
City	Virtual, Online
Period	12/6/21 → 12/14/21

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

Teed, Z., & Deng, J. (2021). DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras. In MA. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, & J. Wortman Vaughan (Eds.), Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021 (pp. 16558-16569). (Advances in Neural Information Processing Systems; Vol. 20). Neural information processing systems foundation.

Teed, Zachary ; Deng, Jia. / DROID-SLAM : Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras. Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. editor / Marc'Aurelio Ranzato ; Alina Beygelzimer ; Yann Dauphin ; Percy S. Liang ; Jenn Wortman Vaughan. Neural information processing systems foundation, 2021. pp. 16558-16569 (Advances in Neural Information Processing Systems).

@inproceedings{12c9f51804d94d4a9cb21d7647ee6ba3,

title = "DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras",

abstract = "We introduce DROID-SLAM, a new deep learning based SLAM system. DROID-SLAM consists of recurrent iterative updates of camera pose and pixelwise depth through a Dense Bundle Adjustment layer. DROID-SLAM is accurate, achieving large improvements over prior work, and robust, suffering from substantially fewer catastrophic failures. Despite training on monocular video, it can leverage stereo or RGB-D video to achieve improved performance at test time. The URL to our open source code is https://github. com/princeton-vl/DROID-SLAM.",

author = "Zachary Teed and Jia Deng",

note = "Publisher Copyright: {\textcopyright} 2021 Neural information processing systems foundation. All rights reserved.; 35th Conference on Neural Information Processing Systems, NeurIPS 2021 ; Conference date: 06-12-2021 Through 14-12-2021",

year = "2021",

language = "English (US)",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

pages = "16558--16569",

editor = "Marc'Aurelio Ranzato and Alina Beygelzimer and Yann Dauphin and Liang, {Percy S.} and {Wortman Vaughan}, Jenn",

booktitle = "Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021",

}

Teed, Z & Deng, J 2021, DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras. in MA Ranzato, A Beygelzimer, Y Dauphin, PS Liang & J Wortman Vaughan (eds), Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. Advances in Neural Information Processing Systems, vol. 20, Neural information processing systems foundation, pp. 16558-16569, 35th Conference on Neural Information Processing Systems, NeurIPS 2021, Virtual, Online, 12/6/21.

DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras. / Teed, Zachary; Deng, Jia.
Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. ed. / Marc'Aurelio Ranzato; Alina Beygelzimer; Yann Dauphin; Percy S. Liang; Jenn Wortman Vaughan. Neural information processing systems foundation, 2021. p. 16558-16569 (Advances in Neural Information Processing Systems; Vol. 20).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - DROID-SLAM

T2 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021

AU - Teed, Zachary

AU - Deng, Jia

PY - 2021

Y1 - 2021

N2 - We introduce DROID-SLAM, a new deep learning based SLAM system. DROID-SLAM consists of recurrent iterative updates of camera pose and pixelwise depth through a Dense Bundle Adjustment layer. DROID-SLAM is accurate, achieving large improvements over prior work, and robust, suffering from substantially fewer catastrophic failures. Despite training on monocular video, it can leverage stereo or RGB-D video to achieve improved performance at test time. The URL to our open source code is https://github. com/princeton-vl/DROID-SLAM.

AB - We introduce DROID-SLAM, a new deep learning based SLAM system. DROID-SLAM consists of recurrent iterative updates of camera pose and pixelwise depth through a Dense Bundle Adjustment layer. DROID-SLAM is accurate, achieving large improvements over prior work, and robust, suffering from substantially fewer catastrophic failures. Despite training on monocular video, it can leverage stereo or RGB-D video to achieve improved performance at test time. The URL to our open source code is https://github. com/princeton-vl/DROID-SLAM.

UR - http://www.scopus.com/inward/record.url?scp=85121844084&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85121844084&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85121844084

T3 - Advances in Neural Information Processing Systems

SP - 16558

EP - 16569

BT - Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021

A2 - Ranzato, Marc'Aurelio

A2 - Beygelzimer, Alina

A2 - Dauphin, Yann

A2 - Liang, Percy S.

A2 - Wortman Vaughan, Jenn

PB - Neural information processing systems foundation

Y2 - 6 December 2021 through 14 December 2021

ER -

Teed Z, Deng J. DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras. In Ranzato MA, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J, editors, Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. Neural information processing systems foundation. 2021. p. 16558-16569. (Advances in Neural Information Processing Systems).

DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this