AI Paper Atlas

Research map / Point clouds / Registration and matching

PEAL: Prior-Embedded Explicit Attention Learning for Low-Overlap Point Cloud Registration

Junle Yu, Luwei Ren, Yu Zhang, Wenhui Zhou, Lili Lin, Guojun Dai

CVPR 2023 · Point clouds › Registration and matching · approach: Learned feature-based registration · 81 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
Apply PEAL rather than GeoTransformerPoint cloud registration · 3DLoMatchRegistration Recall (%): 75.0 -> 81.7Improved
Apply PEAL rather than GeoTransformerPoint cloud registration · 3DMatchFeature Matching Recall (%): 97.9 -> 99.0Improved
Use non-anchor-to-anchor one-way attention instead of no one-way attention (ablation)PEAL-3dprior · 3DLoMatchRegistration Recall (%): 74.0 -> 78.8Improved
Reverse the attention direction to anchor-to-non-anchor (ablation)PEAL-3dprior · 3DLoMatchRegistration Recall (%): 74.0 -> 16.8Hurt
Use bidirectional attention (ablation)PEAL-3dprior · 3DLoMatchRegistration Recall (%): 74.0 -> 71.6Hurt
Replace explicit attention with prior-embedded implicit attention (ablation)PEAL-3dprior · 3DLoMatchRegistration Recall (%): 78.8 -> 74.7Hurt
Select anchor superpoints randomly (ablation)PEAL-3dprior · 3DLoMatchRegistration Recall (%): 78.8 -> 73.8Hurt
Restrict anchors to a random 40% of the base region (ablation)PEAL-3dprior · 3DMatchRegistration Recall (%): 94.1 -> 93.5Hurt
Expand the anchor region by 16 nearest superpoints (ablation)PEAL-3dprior · 3DLoMatchRegistration Recall (%): 78.8 -> 77.2Hurt
Use more image views to obtain 2D overlap prior (ablation)PEAL-2dprior · 3DLoMatchRegistration Recall (%): 78.8 -> 81.2Improved
Add iterative transformation updates (ablation)PEAL-3dprior · 3DLoMatchRegistration Recall (%): 77.8 -> 78.8Improved
Plug PEAL into PredatorPredator · 3DLoMatch (5000 sampled points)Registration Recall (%): 59.8 -> 70.2Improved

Later papers that compared with this method

9 later accepted papers report PEAL as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

1 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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