AI Paper Atlas

Research map / Point clouds / Registration and matching

PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry

Yu Zhang, Junle Yu, Xiaolin Huang, Wenhui Zhou, Ji Hou

ECCV 2022 · Point clouds › Registration and matching · approach: Learned feature-based registration · 39 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 PCR-CG color feature projectionPredator · 3DLoMatch (5000 points)Registration Recall %: 59.8 -> 66.3Improved
add PCR-CGPredator · 3DLoMatch (500 points)Registration Recall %: 60.8 -> 68.5Improved
add PCR-CGPredator · 3DMatch (1000 points)Registration Recall %: 90.6 -> 90.0No clear effect
add PCR-CGCoFiNet · 3DLoMatch (5000 points)Registration Recall %: 64.4 -> 67.9Improved
add PCR-CGGeoTransformer · 3DLoMatchRegistration Recall %: 74.0 -> 76.4Improved
add PCR-CGGeoTransformer · 3DMatchRegistration Recall %: 91.5 -> 92.5Improved
use explicit instead of implicit projection (Pri3D features) (ablation)PCR-CG · 3DLoMatch RR 5000Registration Recall %: 63.4 -> 66.3Improved
use explicit instead of implicit projection (RGB values) (ablation)PCR-CG · 3DLoMatch RR 5000Registration Recall %: 60.5 -> 60.4No clear effect
lift deep Pri3D features instead of RGB values (ablation)PCR-CG · 3DLoMatch RR 5000Registration Recall %: 60.4 -> 66.3Improved
lift deep Pri3D features instead of SIFT features (ablation)PCR-CG · 3DLoMatch RR 5000Registration Recall %: 64.8 -> 66.3Improved
use window size 11x11 instead of 3x3 (ablation)PCR-CG · 3DLoMatch RR 5000Registration Recall %: 63.1 -> 66.3Improved
use 2 views instead of 1 (ablation)PCR-CG · 3DLoMatch RR 5000Registration Recall %: 62.0 -> 63.4Improved

Later papers that compared with this method

1 later accepted paper reports PCR-CG as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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