AI Paper Atlas

Research map / Point clouds / Registration and matching

Transformation Decoupling Strategy Based on Screw Theory for Deterministic Point Cloud Registration With Gravity Prior

Xinyi Li, Zijian Ma, Yinlong Liu, Walter M. X. Zimmer, Hu Cao, Feihu Zhang, Alois Knoll

TPAMI 2024 · Point clouds › Registration and matching · approach: Robust inlier selection for registration

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 the screw-theory decoupled three-stage search instead of FMP+BnBregistration with gravity prior · Synthetic, 95% outliers, 100k correspondencesmedian running time (s): 647.7 -> 0.097Improved
use the decoupled method instead of GROR at 1000k correspondencesregistration with gravity prior · Synthetic, 95% outliers, 1000k correspondencesmedian running time (s): >1800 -> 1.905Improved
increase correspondences from 10k to 1000kOurs · Synthetic, 95% outliersmedian running time (s): 0.009 -> 1.905Mixed
use the decoupled method instead of FGRregistration with gravity prior · WHU-TLSaverage translation error (m): 37.96 -> 0.165Improved
use the decoupled method instead of FMP+BnBregistration with gravity prior · WHU-TLSaverage translation error (m): 12.51 -> 0.165Improved
raise outlier rate from 40% to 80%Ours · Synthetic, N=2000running timeImproved
use the decoupled method instead of RANSAC at 98% outlier rateregistration with gravity prior · Synthetic, N=2000, 98% outliersspeed: approximately 3x10^4 times fasterImproved
use the decoupled method instead of GROR on A9 rotation errorregistration with gravity prior · A9average rotation error (deg): 1.652 -> 0.394Improved
add FMP preprocessing to BnB (ablation)BnB · ETH-Archaverage running time (s): 18.12 -> 7.722Improved

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