AI Paper Atlas

Research map / Point clouds / Registration and matching

Point Set Registration With Global-Local Correspondence and Transformation Estimation

Su Zhang, Yang Yang, Kun Yang, Yi Luo, Sim-Heng Ong

ICCV 2017 · Point clouds › Registration and matching · approach: Non-rigid point set registration · 42 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 the shape distance local feature to the Euclidean global feature in the Gaussian mixture (ablation)GL-CATE · Synthesized fish point set registrationregistration qualityImproved
use elliptical Gaussian soft count with theta = 3 instead of binary count (theta = 0) (ablation)shape distance · Table 1 shape distances of five mannersshape distance discrimination: theta=0: 2, 2, 2, 2; theta=3: 0.5708, 1.9058, 3.6220, 6.8896Improved
use rho = 1, theta = 2 instead of rho = 1, theta = 1 (ablation)GL-CATE · Synthesized contours with rotationaverage errorMixed
estimate sigma^2 by the least-squares formula (14) instead of exponential annealing under noise (ablation)GL-CATE · Noise-contaminated point setsregistration performanceImproved
replace GL-CATE by PR-GLS on car matchingpoint set matching · Car (matching rate)matching rate (%): 92.06% -> 94.68%Improved
GL-CATE versus GLMDTPS on motorbike matchingpoint set matching · Motorbike (matching rate)matching rate (%): 99.40% -> 93.98%Hurt
GL-CATE versus PR-GLS on retinal image registrationimage registration · Retinal imagesRMSE: 4.46 ± 0.64 -> 3.08 ± 0.64Improved
GL-CATE versus PR-GLS on fingerprint image registrationimage registration · Fingerprint imagesRMSE: 7.15 ± 5.67 -> 5.34 ± 3.05Improved
GL-CATE versus CPD on remote sensing image registrationimage registration · Remote sensing imagesRMSE: 1.96 ± 1.09 -> 0.88 ± 0.47Improved

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