Research map / Point clouds / Registration and matching
Toward Zero-Shot Point Cloud Registration Across Diverse Scales, Scenes, and Sensor Setups
Hyungtae Lim, Minkyun Seo, Luca Carlone, JaeSik Park
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 all three scales instead of middle only (ablation) | BUFFER-X · 3DMatch | success rate: 93.38 -> 95.58 | Improved |
| use all three scales instead of middle only (ablation) | BUFFER-X · 3DMatch | speed (Hz): 5.47 -> 1.81 | Hurt |
| use middle scale instead of local only (ablation) | BUFFER-X · 3DMatch | success rate: 84.06 -> 93.38 | Improved |
| use all three scales instead of middle only (ablation) | BUFFER-X · TIERS (trained on 3DMatch) | success rate: 90.80 -> 93.45 | Improved |
| add oracle tuning of voxel size and radius | BUFFER · KITTI (trained on 3DMatch) | success rate: 0.00 -> 99.46 | Improved |
| add scale alignment on top of oracle tuning | GeoTransformer · TIERS (trained on 3DMatch) | success rate: 5.06 -> 92.99 | Improved |
| add scale alignment on top of oracle tuning | Predator · KITTI (trained on 3DMatch) | success rate: 0.00 -> 77.29 | Improved |
| use BUFFER-X instead of BUFFER with oracle tuning | BUFFER-X · Heterogeneous Vel16->OS128 | success rate: 66.77 -> 84.32 | Improved |
| replace RANSAC with KISS-Matcher solver in early exit (tau_N=50) (ablation) | BUFFER-X-Lite · 3DMatch | success rate / speed: 94.54 -> 94.95; 5.19 Hz -> 4.72 Hz | Mixed |
| raise early-exit threshold tau_N from 10 to 50 with KISS-Matcher solver (ablation) | BUFFER-X-Lite · 3DMatch | success rate: 93.94 -> 94.95 | Improved |
| reduce N_FPS to 500 (ablation) | BUFFER-X · 12-dataset benchmark | average recall: reduces recall by 2.71 points | Hurt |
| vary radius ratios, voxel coefficients or sphericity threshold (ablation) | BUFFER-X · 12-dataset benchmark | average recall: at most 0.44 percentage points | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BUFFER — BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration (CVPR 2023) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes (ICCV 2025 · similarity 0.96)
- BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration (CVPR 2023 · similarity 0.91)
- Zero-shot RGB-D Point Cloud Registration with Pre-trained Large Vision Model (CVPR 2025 · similarity 0.89)
- FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators (ICLR 2024 · similarity 0.88)
- Unlocking Generalization Power in LiDAR Point Cloud Registration (CVPR 2025 · similarity 0.88)
- GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields (NeurIPS 2024 · similarity 0.88)
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.
