AI Paper Atlas

Research map / Point clouds / Registration and matching

Deep Closest Point: Learning Representations for Point Cloud Registration

Yue Wang, Justin M. Solomon

ICCV 2019 · Point clouds › Registration and matching · approach: Learned feature-based registration · 1,181 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
use DGCNN instead of PointNet embedding (ablation)DCP-v2 · ModelNet40 (unseen point clouds)RMSE(R) degrees: 7.061375 -> 1.143385Improved
use DGCNN instead of PointNet embedding (ablation)DCP-v1 · ModelNet40 (unseen point clouds)RMSE(R) degrees: 4.124127 -> 2.545697Improved
use SVD layer instead of MLP to output rigid transform (ablation)DCP-v2 · ModelNet40 (unseen point clouds)RMSE(R) degrees: 3.150191 -> 1.143385Improved
use SVD layer instead of MLP to output rigid transform (ablation)DCP-v1 · ModelNet40 (unseen point clouds)RMSE(R) degrees: 4.595206 -> 2.545697Improved
add Transformer attention module (DCP-v1 to DCP-v2) (ablation)DCP · ModelNet40 (unseen point clouds)RMSE(R) degrees: 2.545697 -> 1.143385Improved
add Transformer attention module (DCP-v1 to DCP-v2) (ablation)DCP · ModelNet40 (unseen categories)RMSE(R) degrees: 4.381938 -> 3.150191Improved
increase embedding dimension from 512 to 1024 (ablation)DCP-v2 · ModelNet40 (unseen point clouds)RMSE(R) degrees: 1.143385 -> 1.103424Improved
increase embedding dimension from 512 to 1024 (ablation)DCP-v1 · ModelNet40 (unseen point clouds)RMSE(R) degrees: 2.545697 -> 2.700225Hurt
initialize ICP with DCP outputICP · ModelNet40 (unseen point clouds)RMSE(R) degreesImproved
use DCP-v2 instead of ICPrigid registration · ModelNet40 (unseen point clouds)RMSE(R) degrees: 29.914835 -> 1.143385Improved
evaluate on unseen categories instead of unseen point cloudsDCP-v2 · ModelNet40RMSE(R) degrees: 1.143385 -> 3.150191Hurt
add Gaussian noise to test point cloudsFGR · ModelNet40RMSE(R) degrees: 9.362772 -> 24.651468Hurt

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