Research map / 3D vision / Human pose estimation
A Region-Based Gauss-Newton Approach to Real-Time Monocular Multiple Object Tracking
Henning Tjaden, Ulrich Schwanecke, Elmar Schömer, Daniel Cremers
Read the paperCheck 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 changed | Where | Measured | Effect |
|---|---|---|---|
| use Gauss-Newton-like second-order optimization instead of first-order gradient descent | PWP3D · screwdriver 360 degree rotation sequence | tracking success | Improved |
| use region-based Gauss-Newton with tclc-histograms instead of PWP3D | PWP3D · OPT dataset (Bike) | AUC: 5.358 -> 11.903 | Improved |
| use proposed method instead of ORB-SLAM2 on weakly textured objects | ORB-SLAM2 · OPT dataset (Bike) | AUC: 10.410 -> 11.903 | Improved |
| use proposed method instead of ORB-SLAM2 on well-textured objects | ORB-SLAM2 · OPT dataset (House) | AUC: 17.283 -> 10.150 | Hurt |
| use proposed method instead of ORB-SLAM2 on Soda | ORB-SLAM2 · OPT dataset (Soda) | AUC: 13.444 -> 8.861 | Hurt |
| replace previous Gauss-Newton-like scheme with systematic Gauss-Newton on reweighted least squares | previous tclc-histogram tracker · RBOT regular (Ape) | tracking success (%): 62.1 -> 85.0 | Improved |
| replace previous scheme with proposed method | previous tclc-histogram tracker · RBOT regular (Glue) | tracking success (%): 20.2 -> 38.9 | Improved |
| replace previous scheme with proposed method | previous tclc-histogram tracker · RBOT regular (Cat) | tracking success (%): 96.7 -> 95.9 | Hurt |
| replace previous scheme with proposed method | previous tclc-histogram tracker · RBOT noisy + dynamic light (Egg Box) | tracking success (%): 2.3 -> 11.2 | Improved |
| replace previous scheme with proposed method | previous tclc-histogram tracker · RBOT unmodelled occlusion (Cube) | tracking success (%): 39.6 -> 68.7 | Improved |
Closest papers by meaning
- Real-Time Monocular Pose Estimation of 3D Objects Using Temporally Consistent Local Color Histograms (ICCV 2017 · similarity 0.90)
- SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World (IJCV 2022 · similarity 0.88)
- Gaussian Splatting SLAM (CVPR 2024 · similarity 0.86)
- Free-Moving Object Reconstruction and Pose Estimation with Virtual Camera (AAAI 2025 · similarity 0.85)
- TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels (NeurIPS 2025 · similarity 0.85)
- ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation (NeurIPS 2026 · similarity 0.85)
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.
