AI Paper Atlas

Research map / Point clouds / Registration and matching

Joint Alignment of Multiple Point Sets with Batch and Incremental Expectation-Maximization

Georgios Evangelidis, Radu Horaud

TPAMI 2017 · Point clouds › Registration and matching · approach: Robust inlier selection for registration · 164 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 joint registration with a common GMM (JRMPC-B) instead of one-vs-all pairwise methodsICP, CPD, GMMReg, SimReg · simulated Bunny/Lucy/Armadillo (SNR=10dB, 30% outliers)indirect rotation error std: 0.047 -> 0.008 (Bunny vs ICP)Improved
use JRMPC-B instead of MATrICPMATrICP · Dragon without noiserotation error (degrees): 0.62 -> 0.47Improved
use JRMPC-B instead of MATrICPMATrICP · Bunny without noiserotation error (degrees): 0.27 -> 0.37Hurt
use JRMPC-B instead of MATrICP with SNR 25dB noiseMATrICP · Bunny with noiserotation error (degrees): 2.37 -> 1.07Improved
use JRMPC-B instead of MAICP with noiseMAICP · Happy Buddha with noiserotation error (degrees): 4.13 -> 1.18Improved
use batch JRMPC-B instead of incremental JRMPC-IJRMPC-I · Bunny without noiserotation error (degrees): 0.69 -> 0.37Improved
use incremental JRMPC-I instead of motion averaging under noiseMAICP, MATrICP · Dragon with noiserotation error (degrees): 1.55 -> 0.89Improved
use fixed matches (MV-ICP)JRMPC · multi-view registrationrotation error: 3.75 on Dragon without noiseHurt
fix the variance for initial iterations (ablation)JRMPC-B · multi-view registrationconvergence levelImproved
keep priors constant instead of updating (ablation)JRMPC · simulated dataregistration qualityNo clear effect
use JRMPC-I with hierarchical scheme instead of SLAM method on fr2/deskElastic fusion, RGBD SLAM · TUM fr2/desktranslation RMSE (m): 0.071 -> 0.034Improved
use JRMPC-I instead of ORB-SLAM2ORB-SLAM2 · TUM fr1/desktranslation RMSE (m): 0.016 -> 0.047Hurt

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