atlas

Research map / 3D vision / Depth and stereo

Robust, Real-Time 3D Tracking of Multiple Objects With Similar Appearances

CVPR 2016 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 21 citations (OpenAlex)

Check 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 automatic detection and tracking of artifacts (ablation)Proposed 3D tracker · All seven sequencesMOTA: 0.858 -> 0.898Helped
Use semiparametric PDFs instead of a Gaussian PDF for 3D target shapes (ablation)Proposed 3D tracker · All seven sequencesMOTA: 0.878 -> 0.898Helped
Use the track graph to constrain candidate target labels in MAP-EM (ablation)Proposed 3D tracker · All seven sequencesMOTA: 0.864 -> 0.898Helped
Use the track graph to constrain MAP-EM (ablation)Proposed 3D tracker · APIDISFPS: 13 FPS -> 26 FPSHelped
Use the track graph to constrain MAP-EM (ablation)Proposed 3D tracker · ICG-Lab-6FPS: 11 FPS -> 25 FPSHelped

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