Research map / 3D vision / Human pose estimation
Optimal Transformation Estimation With Semantic Cues
Danda Pani Paudel, Adlane Habed, Luc Van Gool
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 |
|---|---|---|---|
| decrease homography bound gap (ablation) | Branch-and-prune registration · Altstadt ellipse estimation | ellipse area | Improved |
| increase object size with fixed number of support points (ablation) | Branch-and-prune registration · Simulated detections, Altstadt | homography accuracy | Hurt |
| use 25 support points instead of 20 (ablation) | Branch-and-prune registration · Simulated detections, Altstadt | running time | Hurt |
| use 30 support points instead of 25 (ablation) | Branch-and-prune registration · Simulated detections, Altstadt | running time | Improved |
| use automatic instead of manual semantic labels (ablation) | Ours · Altstadt | rotation error dR (degrees): 6.6918 -> 2.97 | Improved |
| use automatic instead of manual semantic labels (ablation) | Ours · Sechselautenplatz | rotation error dR (degrees): 15.48 -> 6.28 | Improved |
| use automatic instead of manual semantic labels (ablation) | Ours · ZurichWest | rotation error dR (degrees): 17.21 -> 10.31 | Improved |
| use ours instead of SSR | 3D-to-3D projective registration · Fountain-P11 | time (sec): 238.0209 -> 47.7201 | Improved |
| use ours instead of SSR | 3D-to-3D projective registration · Herz-Jesu-P8 | time (sec): 348.8915 -> 50.1480 | Improved |
| use ours instead of SSR | 3D-to-3D projective registration · Fountain-P11 | rotation RMS error (degrees): 8.1879 -> 1.5881 | Improved |
Closest papers by meaning
- Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence (CVPR 2025 · similarity 0.86)
- Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps (CVPR 2024 · similarity 0.86)
- Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence (CVPR 2024 · similarity 0.86)
- Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondence (CVPR 2025 · similarity 0.86)
- Partial-to-Partial Shape Matching with Geometric Consistency (CVPR 2024 · similarity 0.85)
- GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers (ICLR 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.
