AI Paper Atlas

Research map / 3D vision / 3D generation

Joint Spatial-Temporal Optimization for Stereo 3D Object Tracking

Peiliang Li, Jieqi Shi, Shaojie Shen

CVPR 2020 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 22 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
add stereo spatial alignment to monocular regressed 3D boxes (ablation)Mono Regress · KITTI tracking valMOTA: -35.26 -> 26.86Improved
add temporal geometric constraints to spatial alignment (ablation)Stereo 3D tracking · KITTI tracking valMOTA: 26.86 -> 29.39Improved
use reprojection error instead of local-coordinate patch alignment for temporal constraints (ablation)Joint spatial-temporal optimization · KITTI tracking val, 3D IoU = 0.25MOTA: 56.14 -> 56.70Improved
use reprojection error instead of local-coordinate patch alignment for temporal constraints (ablation)Joint spatial-temporal optimization · KITTI tracking val, 3D IoU = 0.5MOTA: 28.56 -> 29.39Improved
use local-coordinate alignment instead of reprojection error for temporal constraints (ablation)Joint spatial-temporal optimization · KITTI tracking valMOTA: 29.39 -> 28.56Hurt

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