AI Paper Atlas

Research map / Point clouds / Registration and matching

Rethinking Point Cloud Registration as Masking and Reconstruction

Guangyan Chen, Meiling Wang, Li Yuan, Yi Yang, Yufeng Yue

ICCV 2023 · Point clouds › Registration and matching · approach: Learned feature-based registration · 17 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 the Masked Reconstruction Auxiliary Network (MRA) during training (ablation)MRT · 3DLoMatchRR (%): 67.8 -> 75.4Improved
add MRA to PredatorPredator · 3DLoMatchRR (%): 62.5 -> 67.3Improved
add MRA to GeoTRGeoTR · 3DLoMatchRR (%): 75.0 -> 77.1Improved
add MRA to RegTRRegTR · 3DLoMatchRR (%): 64.8 -> 71.0Improved
additionally randomly mask point patches before the encoder (ablation)MRT · 3DLoMatchRR (%): 75.4 -> 73.6Hurt
use transformed center points for mask token positional encodings (ablation)MRT · 3DLoMatchRR (%): 71.6 -> 75.4Improved
also reconstruct overlapping regions of the other point cloud (ablation)MRT · 3DLoMatchRR (%): 73.2 -> 75.4Improved
use l2 Chamfer loss instead of l1 (ablation)MRT · 3DLoMatchRR (%): 72.4 -> 75.4Improved
use l2 Chamfer loss instead of l1+l2 (ablation)MRT · 3DMatchRR (%): 95.1 -> 95.1No clear effect
add Deviation Correction module (ablation)MRT · 3DLoMatchRR (%): 73.5 -> 75.4Improved
predict deviation compensation instead of directly projecting coordinates (ablation)MRT · 3DLoMatchRR (%): 71.0 -> 75.4Improved
add overlap prediction handled in full model vs without overlap reconstruction on 3DMatch RRE (ablation)MRT · 3DMatchRRE (deg): 1.453 -> 1.324Improved

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