AI Paper Atlas

Research map / Point clouds / Registration and matching

Learning Multiview 3D Point Cloud Registration

Zan Gojcic, Caifa Zhou, Jan D. Wegner, Leonidas J. Guibas, Tolga Birdal

CVPR 2020 · Point clouds › Registration and matching · approach: Learned feature-based registration · 200 citations (OpenAlex)

Check 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
Use the learned pairwise registration network instead of descriptor matching with RANSAC3DMatch pairwise registration · 3DMatchregistration recall: 0.86 -> 0.87Improved
Add iterative refinement using previous weights and residuals (ablation)Ours pairwise registration · 3DMatchregistration recall: 0.87 -> 0.89Improved
Synchronize pairwise estimates into global posesOurs multiview registration · ScanNet (Ours, Good)rotation ECDF at 3°: 57.7 -> 65.8Improved
Synchronize pairwise estimates into global posesOurs multiview registration · ScanNet (Ours, Good)translation ECDF at 0.05 m: 44.8 -> 48.4Improved
Use confidence-estimation edge pruning rather than no edge pruning (ablation)Ours multiview registration · ScanNetregistration performanceImproved
Use local and global confidence combined by harmonic mean rather than relying only on local confidence (ablation)Ours transformation synchronization · ScanNetregistration performanceImproved
Prune low-confidence edges before transformation synchronization (ablation)Ours multiview registration · ScanNetregistration performanceImproved
Feed iterative weights and residuals back when outliers are prevalent or edge pruning is ineffective (ablation)Ours pairwise registration · ScanNetregistration performanceHurt
Increase the edge-pruning threshold above 0.2 (ablation)Ours multiview registration · ScanNetangular and translation errorsNo clear effect
Replace RANSAC with the learned softNN pairwise registration3DMatch Kitchen scene · 3DMatch Kitchen scene (60 fragments)total runtime (s): 1106.3 -> 80.3Improved

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