Research map / 3D vision / Depth and stereo
Fine-To-Coarse Global Registration of RGB-D Scans
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use fine-to-coarse global registration instead of Xiao et al.'s registration | RGB-D scan registration · SUN3D benchmark (25 scenes) | RMSE median (m): 0.255 -> 0.065 | Helped |
| Use fine-to-coarse global registration instead of Choi et al.'s registration | RGB-D scan registration · SUN3D benchmark (25 scenes) | RMSE median (m): 0.224 -> 0.065 | Helped |
| Add fine-to-coarse iteration to ICP (ablation) | ICP registration · SUN3D benchmark | registration error | Helped |
| Add a structural model (ablation) | Fine-to-coarse RGB-D registration · SUN3D benchmark | registration error | Helped |
| Add fine-to-coarse iteration (ablation) | RGB-D registration with structural modeling · SUN3D benchmark | registration error | Helped |
Closest papers by meaning
- CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage (NeurIPS 2026 · similarity 0.85)
- Zero-shot RGB-D Point Cloud Registration with Pre-trained Large Vision Model (CVPR 2025 · similarity 0.83)
- Multi-scale Consistency for Robust 3D Registration via Hierarchical Sinkhorn Tree (NeurIPS 2024 · similarity 0.83)
- HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions (AAAI 2025 · similarity 0.83)
- Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping (NeurIPS 2025 · similarity 0.83)
- FastMAC: Stochastic Spectral Sampling of Correspondence Graph (CVPR 2024 · similarity 0.82)
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.