AI Paper Atlas

Research map / 3D vision / Depth and stereo

Event-Based Visual Inertial Odometry

Alex Zihao Zhu, Nikolay Atanasov, Kostas Daniilidis

CVPR 2017 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 257 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
use event-based feature tracking instead of image-based KLT tracking, with the same EKF pipelineVisual-inertial odometry · hdr boxesMean Position Error (%): 5.65 -> 1.23Improved
use event-based feature tracking instead of image-based KLT tracking, with the same EKF pipelineVisual-inertial odometry · dynamic translationMean Position Error (%): 2.12 -> 1.90Improved
use event-based feature tracking instead of image-based KLT tracking, with the same EKF pipelineVisual-inertial odometry · shapes translationMean Position Error (%): 1.98 -> 2.42Hurt
use event-based feature tracking instead of image-based KLT tracking, with the same EKF pipelineVisual-inertial odometry · poster translationMean Position Error (%): 0.97 -> 0.94Improved
use event-based feature tracking instead of image-based KLT tracking, with the same EKF pipelineVisual-inertial odometry · poster 6dofMean Position Error (%): 2.17 -> 3.56Hurt
use event-based feature tracking instead of image-based KLT tracking, with the same EKF pipelineVisual-inertial odometry · hdr posterMean Position Error (%): 2.67 -> 2.63Improved
use event-based feature tracking instead of image-based KLT tracking, with the same EKF pipelineVisual-inertial odometry · boxes translationMean Position Error (%): 2.28 -> 2.69Hurt
use event-based feature tracking instead of image-based KLT tracking, with the same EKF pipelineVisual-inertial odometry · boxes 6dofMean Position Error (%): 2.91 -> 3.61Hurt
use event-based feature tracking instead of image-based KLT tracking, with the same EKF pipelineVisual-inertial odometry · dynamic 6dofMean Position Error (%): 4.49 -> 4.07Improved

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