AI Paper Atlas

Research map / Point clouds / Registration and matching

Cross3DReg: A Real-world Cross-source Point Cloud Registration Benchmark

Zongyi Xu, Z. Lang, Yilong Chen, Shanshan Zhao, Xiaoshui Huang, Sean Bin Yang, Yan Zhang, Qianni Zhang, Xinbo Gao

IJCV 2026 · Point clouds › Registration and matching · approach: Learned feature-based registration · 0 citations (OpenAlex)

Read the paper

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 overlapping mask prediction (OMP) with unaligned images (ablation)geometric self-attention matcher · Cross3DReg (LGR)RRE (deg): 18.184 -> 8.371Improved
add overlapping mask prediction (OMP) (ablation)geometric self-attention matcher · Cross3DReg (LGR)RR (%): 81.7 -> 86.7Improved
replace geometric self-attention with visual-geometric attention matching (VGAM) (ablation)OMP with geometric self-attention · Cross3DReg (LGR)RRE (deg): 8.371 -> 6.683Improved
replace vanilla self-attention with visual-geometric attention matching (VGAM) (ablation)OMP with vanilla self-attention · Cross3DReg (LGR)RTE (m): 1.242 -> 1.010Improved
use geometric instead of vanilla self-attention with OMP (ablation)OMP · Cross3DReg (LGR)RTE (m): 1.242 -> 1.287Hurt
use Cross3DReg instead of GeoTransGeoTrans · Cross3DReg (LGR)RR (%): 81.7 -> 87.1Improved
use Cross3DReg instead of GeoTransGeoTrans · Cross3DReg (LGR)RRE (deg): 18.15 -> 6.68Improved
use RANSAC-50K estimator with Cross3DRegCross3DReg vs Geotrans · Cross3DReg (RANSAC-50K)RR (%): 72.2 -> 78.6Improved
use weighted SVD estimator with Cross3DRegCross3DReg vs Geotrans · Cross3DReg (Weighted SVD)RR (%): 62.9 -> 57.8Hurt
use same-source methods (FCGF, Predator, CoFiNet, Omnet) on cross-source datasame-source registration · Cross3DReg (LGR)RR (%): 0.0Hurt

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