AI Paper Atlas

Research map / Point clouds / Registration and matching

Match Normalization: Learning-Based Point Cloud Registration for 6D Object Pose Estimation in the Real World

Zheng Dang, Lizhou Wang, Yu Guo, Mathieu Salzmann

TPAMI 2024 · Point clouds › Registration and matching · approach: Learned feature-based registration · 23 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 Match Normalization (ablation)Ours-DCP · TUD-LRotation mAP 5 deg: 0.21 -> 0.91Improved
add Match Normalization (ablation)Ours-DCP · TUD-LBOP AR: 0.27 -> 0.90Improved
add Match Normalization (ablation)Ours-DCP · TUD-Lpredicted matches: 24.84 -> 276.10Improved
add Match Normalization (ablation)Ours-DCP · TUD-Ltrue inlier matches: 10.44 -> 262.96Improved
replace SVD loss with NLL loss (ablation)DCP(v2) · ModelNet40 (full rotation range)Rotation mAP 5 deg: 0.00 -> 0.35Improved
replace SVD loss with NLL loss (ablation)DCP(v2) · ModelNet40 (45 deg range)Rotation mAP 5 deg: 0.36 -> 0.72Improved
add ICP post-processingOurs-DCP · TUD-LBOP AR: 0.801 -> 0.903Improved
add ICP post-processingOurs-DCP · LINEMODBOP AR: 0.446 -> 0.678Improved
add ICP post-processingOurs-DCP · Occluded-LINEMODBOP AR: 0.365 -> 0.544Improved
add Match Normalization and NLL loss (Ours-DCP)DCP(v2) · TUD-LBOP AR: 0.038 -> 0.801Improved
add Match NormalizationIDAM · TUD-LBOP AR: 0.091 -> 0.444Improved
add Match NormalizationIDAM · LINEMODBOP AR: 0.067 -> 0.184Improved

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