AI Paper Atlas

Research map / 3D vision / Depth and stereo

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

NeurIPS 2021 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 231 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add global bundle adjustment backend with loop closure (ablation)DROID-SLAM odometry · EuRoC monocularATE: 0.186 -> 0.022Helped
add global optimization and stereo input (ablation)DROID-SLAM · TartanAir validationATEHelped
add global context via spatial pooling in GRU (ablation)DROID-SLAM update operator · TartanAir validationATEHelped
train with DBA layer instead of training on flow and applying BA at test (ablation)DROID-SLAM · TartanAir validationATE / failure rateHelped
DROID-SLAM vs top competition entriesSLAM · TartanAir test mononormalized RPE: 0.340 -> 0.129Helped
DROID-SLAM vs ORB-SLAM3 stereoSLAM · EuRoC stereoATE: 0.084 -> 0.024Helped
DROID-SLAM vs deep baselinesSLAM · TUM-RGBDATE: 0.233 -> 0.038Helped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy