Research map / 3D vision / Human pose estimation
Real-Time Monocular Pose Estimation of 3D Objects Using Temporally Consistent Local Color Histograms
Henning Tjaden, Ulrich Schwanecke, Elmar Schomer
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 averaged posteriors (8) instead of averaged local energies (5) (ablation) | tclc-histogram detection · ACCV dataset, 100 training images | 2D IoU score: 68.5% -> 78.5% | Improved |
| use averaged posteriors (8) instead of averaged local energies (5) (ablation) | tclc-histogram detection · ACCV dataset, 100 training images | 2D projection score: 28.8% -> 40.2% | Improved |
| use averaged posteriors (8) instead of averaged local energies (5) (ablation) | tclc-histogram detection · ACCV dataset, 100 training images | 6D pose score [11]: 49.8% -> 57.3% | Improved |
| use averaged posteriors (8) instead of averaged local energies (5) (ablation) | tclc-histogram detection · ACCV dataset, 100 training images | 6D pose score [25]: 18.6% -> 26.7% | Improved |
| use averaged posteriors (8) instead of averaged local energies (5) (ablation) | tclc-histogram tracking · Semi-synthetic driller sequence | silhouette pose ambiguity count: twice -> once | Improved |
| add temporal consistency to local color histograms (ablation) | local histogram segmentation · Semi-synthetic driller sequence | tracking success | Improved |
| replace global histograms by local tclc-histograms | tracking of [26] · Semi-synthetic driller sequence | tracking success | Improved |
| replace global histograms by local tclc-histograms | tracking of [26] · Real drill sequence with clutter | tracking success | Improved |
| add temporal consistency to local color histograms (ablation) | local histogram segmentation · Real drill sequence with clutter | tracking success | Improved |
| use averaged posteriors (8) instead of (5) for pose recovery (ablation) | tclc-histogram pose detection · Real drill sequence with clutter | recovery after leaving field of view | Improved |
| increase number of training images from 25 to 200 | tclc-histogram detection · ACCV dataset | detection score | Improved |
| compare against LINE-2D on 2D IoU | tclc-histogram detection · ACCV dataset, 100 training images | 2D IoU score: 86.5% -> 78.5% | Hurt |
Closest papers by meaning
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.87)
- Free-Moving Object Reconstruction and Pose Estimation with Virtual Camera (AAAI 2025 · similarity 0.86)
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema (NeurIPS 2026 · similarity 0.86)
- Co-op: Correspondence-based Novel Object Pose Estimation (CVPR 2025 · similarity 0.86)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (CVPR 2025 · similarity 0.86)
- MFOS: Model-Free & One-Shot Object Pose Estimation (AAAI 2024 · 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.
