AI Paper Atlas

Research map / Point clouds / Registration and matching

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

Zheng Dang, Lizhou Wang, Yu Guo, Mathieu Salzmann

ECCV 2022 · Point clouds › Registration and matching · approach: Learned feature-based registration · 24 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)DCP-based registration · TUD-LADD (0.1d): 0.23 -> 0.93Improved
add Match Normalization (ablation)DCP-based registration · TUD-Ltrue inlier matches: 10.44 -> 262.96Improved
add Match Normalization (ablation)DCP-based registration · TUD-Lpredicted matches: 24.84 -> 276.10Improved
replace SVD loss with NLL loss (ablation)DCP(v2) · ModelNet40 partial-to-partial (full rotation)rotation mAP at 5 deg: 0.00 -> 0.35Improved
replace SVD loss with NLL loss (ablation)DCP(v2) · ModelNet40 partial-to-partial (45 deg rotation)rotation mAP at 5 deg: 0.36 -> 0.72Improved
replace SVD loss with NLL loss (ablation)DCP(v2) · ModelNet40 partial-to-partial (full rotation)translation mAP at 0.01: 0.42 -> 0.85Improved
add Match Normalization, NLL loss and Sinkhorn layer to DCPDCP(v2) · TUD-LADD (0.1d): 0.01 -> 0.85Improved
add Match Normalization to IDAMIDAM · TUD-LADD (0.1d): 0.05 -> 0.46Improved
add Match Normalization to IDAMIDAM · LINEMODADD (0.1d): 0.02 -> 0.11Improved
add Match Normalization, NLL loss and Sinkhorn layer to DCPDCP(v2) · LINEMODADD (0.1d): 0.00 -> 0.37Improved
add Match Normalization, NLL loss and Sinkhorn layer to DCPDCP(v2) · Occluded-LINEMODADD (0.1d): 0.00 -> 0.28Improved
add ICP post-processingOurs-DCP · TUD-LADD (0.1d): 0.85 -> 0.93Improved

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