AI Paper Atlas

Research map / Point clouds / Registration and matching

RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning

Chengyu Zheng, Jin Huang, Honghua Chen, Mingqiang Wei

ICCV 2025 · Point clouds › Registration and matching · approach: Learned feature-based registration · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add RARE refinement on top of GeoTransformerGeoTransformer · 3DMatchRegistration Recall (%): 92.0 -> 94.5Improved
Add RARE refinement on top of FCGFFCGF · 3DMatchRegistration Recall (%): 67.9 -> 76.2Improved
Add RARE refinement on top of Predator and CoFiNetPredator, CoFiNet · 3DMatchRegistration Recall (%): 89.0 -> 92.7 (Predator); 89.3 -> 93.0 (CoFiNet)Improved
Add Inlier Aggregation module (ablation)RARE · 3DMatchRegistration Recall (%): 92.8 -> 94.5Improved
Add Feature Transfer module (ablation)RARE · 3DMatchRegistration Recall (%): 93.1 -> 94.5Improved
Add PCA dimensionality reduction of diffusion features (ablation)RARE · 3DMatchRegistration Recall (%): 94.1 -> 94.5No clear effect
Use diffusion layers [0,3,6] instead of single layers or adding layer 9 (ablation)Depth diffusion features · 3DMatch (diffusion features only)Registration Recall (%): 63.3 -> 76.0 (vs [0,3,6,9])Improved
Add extra-large layer 9 features (ablation)Depth diffusion features · 3DMatch (diffusion features only)Registration Recall (%): 76.0 -> 60.9 ([0,3,9] vs [0,3,6])Hurt
Add RARE refinement on top of GeoTransformer on KITTIGeoTransformer · KITTIRegistration Recall (%): 99.8 -> 99.8No clear effect
Add RARE refinement on top of GeoTransformer on KITTIGeoTransformer · KITTIRelative Translation Error: 0.068 -> 0.064Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy