AI Paper Atlas

Research map / Point clouds / Registration and matching

Provably Approximated Point Cloud Registration

Ibrahim Jubran, Alaa Maalouf, Ron Kimmel, Dan Feldman

ICCV 2021 · Point clouds › Registration and matching · approach: Robust inlier selection for registration · 11 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
use provable P-ICP / P-ICP-Refined instead of ICP, CPD and GO-ICP for registrationpoint cloud registration · Armadillo, noise variance 0.01registration error: error smaller by x2-x10 than other methodsImproved
add more sampled subsets to P-RANSAC (about 40 subsets in d=3) (ablation)P-RANSAC · Bunny, Armadillo, Asian Dragon, syntheticapproximation factor alpha: error of at most x1.5 the globally minimal cost after roughly 40 subsetsImproved
use P-RANSAC instead of RANSAC and TEASER++ for alignmentalignment with known correspondences · Bunny, n=2000, noise variance 0.009cost and rotation/translation errorImproved
use M-estimator cost with provable approximationP-ICP · Armadillo with outliers, n=800robustness to outliersImproved
add a single ICP refinement run after P-ICP (ablation)P-ICP · Armadillo registrationcostImproved

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