AI Paper Atlas

Research map / Point clouds / Registration and matching

PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration

Runzhao Yao, Shaoyi Du, Wenting Cui, Canhui Tang, Chengwu Yang

ECCV 2024 · Point clouds › Registration and matching · approach: Learned feature-based registration · 32 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
replace vanilla VN convolution with PARE-Conv (node features) (ablation)PARE-Net backbone · 3DLoMatchRegistration Recall (%): 76.6 -> 78.8Improved
replace vanilla VN convolution with PARE-Conv (edge features) (ablation)PARE-Net backbone · 3DLoMatchRegistration Recall (%): 77.8 -> 80.5Improved
use feature-based hypothesis proposer instead of RANSAC (ablation)PARE-Net pose estimation · 3DLoMatchRegistration Recall (%): 77.5 -> 80.5Improved
use feature-based hypothesis proposer instead of LGR (ablation)PARE-Net pose estimation · 3DLoMatchRegistration Recall (%): 78.9 -> 80.5Improved
use feature-based hypothesis proposer instead of RANSAC (ablation)PARE-Net pose estimation · 3DMatchRegistration Recall (%): 93.7 -> 95.0Improved
add contrastive rotation loss on equivariant features (ablation)PARE-Net · 3DLoMatchRegistration Recall (%): 79.3 -> 80.5Improved
add contrastive rotation loss on equivariant features (ablation)PARE-Net · 3DMatchRegistration Recall (%): 93.3 -> 95.0Improved
use L2 loss on equivariant features instead of no loss (ablation)PARE-Net · 3DLoMatchRegistration Recall (%): 79.3 -> 75.4Hurt
use L2 loss on equivariant features instead of no loss (ablation)PARE-Net · 3DMatchRegistration Recall (%): 93.3 -> 94.2Improved
rotation-equivariant design instead of rotation augmentation only (PARE-Net vs GeoTrans)point cloud registration · Rotated 3DLoMatchTransformation Recall (%): GeoTrans 75.4 -> 72.6 under rotation; Ours 81.3 -> 81.8Improved
PARE-Net vs PEAL in speed and recallPARE-Net · 3DLoMatchTime (s): 1.19 -> 0.17Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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