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

Zachary Teed, Jia Deng

Keywords: SLAM, Simultaneous Localization and Mapping, 3D

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.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://github.com/princeton-vl/DROID-SLAM

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/droid-slam-deep-visual-slam-for-monocular/code)