Timezone: »
Oral
DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras
Zachary Teed · Jia Deng
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 Information
Zachary Teed (Princeton University)
Jia Deng (Princeton University)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Poster: DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras »
Fri. Dec 10th 04:30 -- 06:00 PM Room
More from the Same Authors
-
2020 Poster: Learning to Prove Theorems by Learning to Generate Theorems »
Mingzhe Wang · Jia Deng -
2020 Poster: Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D »
Ankit Goyal · Kaiyu Yang · Dawei Yang · Jia Deng -
2020 Spotlight: Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D »
Ankit Goyal · Kaiyu Yang · Dawei Yang · Jia Deng -
2020 Poster: Strongly Incremental Constituency Parsing with Graph Neural Networks »
Kaiyu Yang · Jia Deng -
2011 Poster: Fast and Balanced: Efficient Label Tree Learning for Large Scale Object Recognition »
Jia Deng · Sanjeev Satheesh · Alexander C Berg · Li Fei-Fei