Research map / Point clouds / Registration and matching
FilterReg: Robust and Efficient Probabilistic Point-Set Registration Using Gaussian Filter and Twist Parameterization
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 |
|---|---|---|---|
| Optimize σ rather than keep it fixed (ablation) | FilterReg · Stanford Bunny | overall time [ms]: 38.4 -> 32.1 | Helped |
| Optimize σ rather than keep it fixed (ablation) | FilterReg · Stanford Bunny | time per iteration [ms]: 0.96 -> 1.16 | Hurt |
| Use the Gaussian-filter correspondence and twist-based M step instead of direct-parameterization Opt | Deformable tracking · Deformable tracking sequence | M step [ms]: 382 -> 21.6 | Helped |
| Run the filter-based E step on GPU rather than CPU | FilterReg · Deformable tracking sequence | E step [ms]: 62 -> 7.8 | Helped |
| Use FilterReg rather than Feature ICP for feature-based registration | Feature-based global registration · 30 RGBD images | success rate: 25/30 -> 29/30 | Helped |
| Use FilterReg rather than Feature ICP for feature-based registration | Feature-based global registration · RGBD images | time [ms]: 34 -> 13 | Helped |
| Use a point-to-plane error rather than a point-to-point error (ablation) | FilterReg · Stanford Lounge | average Euler angle deviation | Helped |
| Use FilterReg rather than projective ICP | DynamicFusion non-rigid tracking · RGBD sequence with fast motion | tracking success | Helped |
Closest papers by meaning
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (CVPR 2024 · similarity 0.86)
- HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions (AAAI 2025 · similarity 0.86)
- GRICP: Granular-Ball Iterative Closest Point with Multikernel Correntropy for Point Cloud Fine Registration (AAAI 2025 · similarity 0.85)
- Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis (CVPR 2024 · similarity 0.85)
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization (NeurIPS 2024 · similarity 0.85)
- Progressive Correspondence Regenerator for Robust 3D Registration (CVPR 2025 · 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.