AI Paper Atlas

Research map / Point clouds / Registration and matching

OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration

Hao Xu, Shuaicheng Liu, Guangfu Wang, Guanghui Liu, Bing Zeng

ICCV 2021 · Point clouds › Registration and matching · approach: Learned feature-based registration · 230 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 mask prediction module without mask supervision (ablation)OMNet baseline · unseen shapes with noise (TS)Error(R): 5.250 -> 5.550Hurt
add mask prediction loss to mask module (ablation)OMNet · unseen shapes with noise (TS)Error(R): 5.550 -> 2.681Improved
add fusion layers before regression (ablation)OMNet · unseen shapes with noise (TS)Error(R): 2.681 -> 1.722Improved
add connection between mask prediction and regression modules (ablation)OMNet · unseen shapes with noise (TS)Error(R): 1.722 -> 1.490Improved
use only top-k points by mask instead of soft mask (k=500) (ablation)OMNet · unseen shapes with noise (TS)Error(R): 1.490 -> 2.255Hurt
reduce top-k from 500 to 100 (ablation)OMNet · unseen shapes with noise (TS)Error(R): 2.255 -> 2.458Hurt
increase mask loss weight lambda from 0.1 to 2.0 (ablation)OMNet · unseen shapes with noise (TS)Error(R): 2.038 -> 1.721Improved
train and test on twice-sampled data instead of once-sampled (unseen shapes) (ablation)OMNet · ModelNet40 unseen shapesError(R): 0.639 -> 0.991Hurt
compare OMNet with PRNet on unseen shapes TSOMNet versus PRNet · ModelNet40 unseen shapes (TS)Error(R): 4.223 -> 0.991Improved
compare OMNet with RPMNet under RPMNet partial mannerOMNet versus RPMNet · ModelNet40 unseen categories with noiseError(R): 4.913 -> 3.834Improved
train on once-sampled data (OS) instead of twice-sampled (TS) for DCP on noise (ablation)DCP · ModelNet40 Gaussian noiseError(R): 6.653 -> 6.024Mixed

Later papers that compared with this method

2 later accepted papers report Omnet as a baseline in their results tables; 2 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 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