AI Paper Atlas

Research map / Point clouds / Point cloud classification

Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration

Xueyang Kang, Zhaoliang Luan, Kourosh Khoshelham, Bing WANG

ECCV 2024 · Point clouds › Point cloud classification · approach: Equivariant point cloud networks · 4 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 learned descriptor layers (ablation)Equi-GSPR · 3DMatchRegistration Recall (%): 61.39 -> 94.60Improved
add equivariant graph layers (ablation)Equi-GSPR · 3DMatchRegistration Recall (%): 62.45 -> 94.60Improved
use equivariant layers instead of normal GCNN (ablation)Equi-GSPR · 3DMatchRegistration Recall (%): 68.52 -> 94.60Improved
add Low-Rank Feature Transformation (ablation)Equi-GSPR · 3DMatchRegistration Recall (%): 83.09 -> 94.60Improved
add rank regularizer (ablation)Equi-GSPR · 3DMatchRegistration Recall (%): 76.45 -> 94.60Improved
add sub-matrix rank verification (ablation)Equi-GSPR · 3DMatchRegistration Recall (%): 87.76 -> 94.60Improved
use ball query instead of kNN graph construction (ablation)Equi-GSPR · 3DMatchRegistration Recall (%): 92.37 -> 94.60Improved
use learned PointNet++ descriptor instead of pre-trained FCGF (ablation)Equi-GSPR · 3DMatchRegistration Recall (%): 93.87 -> 94.60Improved
use learned descriptor instead of hand-crafted FPHF (ablation)Equi-GSPR · 3DMatchRegistration Recall (%): 83.62 -> 94.60Improved
replace descriptor layers with SpinNet equivariant descriptor (ablation)Equi-GSPR · 3DMatchRegistration Recall (%): 94.60 -> 82.16Hurt
increase sampled points from 1024 to 2048 or 4096 (ablation)Equi-GSPR · 3DMatchRegistration Recall (%): 94.6 -> 94.8 (2048), 95.3 (4096)No clear effect
add equivariant layers (latency cost) (ablation)Equi-GSPR · 3DMatchTime (s): 0.06 -> 0.12Hurt

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