AI Paper Atlas

Research map / Point clouds / Registration and matching

CoFiNet: Reliable Coarse-to-fine Correspondences for Robust PointCloud Registration

Hao Yu, Fu Li, Mahdi Saleh, Benjamin Busam, Slobodan Ilic

NeurIPS 2021 · Point clouds › Registration and matching · approach: Robust inlier selection for registration

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 fine-level refinement after coarse matching (ablation)CoFiNet · 3DMatch, 2500 samplesRegistration Recall (%): 79.6 -> 88.9Improved
add fine-level refinement after coarse matching (ablation)CoFiNet · 3DLoMatch, 2500 samplesRegistration Recall (%): 41.2 -> 66.2Improved
use overlap-ratio weighting instead of binary mask at coarse level (ablation)CoFiNet · 3DMatch, 2500 samplesRegistration Recall (%): 87.4 -> 88.9Improved
use overlap-ratio weighting instead of binary mask at coarse level (ablation)CoFiNet · 3DLoMatch, 2500 samplesRegistration Recall (%): 61.5 -> 66.2Improved
add density-adaptive matching module (ablation)CoFiNet · 3DMatch, 2500 samplesRegistration Recall (%): 88.3 -> 88.9Improved
add density-adaptive matching module (ablation)CoFiNet · 3DLoMatch, 2500 samplesRegistration Recall (%): 65.1 -> 66.2Improved
raise coarse threshold tau_c from 0.05 to 0.15 (ablation)CoFiNet · 3DMatch, 2500 samplesInlier Ratio (%): 49.4 -> 55.5Improved
raise coarse threshold tau_c from 0.05 to 0.15 (ablation)CoFiNet · 3DMatch, 2500 samplesRegistration Recall (%): 87.4 -> 85.5Hurt
raise coarse threshold tau_c from 0.05 to 0.15 (ablation)CoFiNet · 3DLoMatch, 2500 samplesRegistration Recall (%): 62.8 -> 58.9Hurt
add minimum coarse correspondence count tau_m=200 (with tau_c=0.20) (ablation)CoFiNet · 3DLoMatch, 2500 samplesRegistration Recall (%): 58.9 -> 66.2Improved
add minimum coarse correspondence count tau_m=200 (with tau_c=0.20) (ablation)CoFiNet · 3DMatch, 2500 samplesInlier Ratio (%): 55.5 -> 51.2Hurt
sample fewer correspondences (5000 to 250) (ablation)CoFiNet · 3DMatchInlier Ratio (%): 49.8 -> 52.2Improved

Later papers that compared with this method

11 later accepted papers report CoFiNet as a baseline in their results tables; 11 of them report a better number on most of the results they share with it.

3 more not listed.

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