AI Paper Atlas

Research map / Point clouds / Registration and matching

Distinctiveness Oriented Positional Equilibrium for Point Cloud Registration

Taewon Min, Chonghyuk Song, Eunseok Kim, Inwook Shim

ICCV 2021 · Point clouds › Registration and matching · approach: Learned feature-based registration · 22 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 DoPE moduleDCP · ModelNet40 full+cleanMAE(R) degrees: 0.770573 -> 0.085278Improved
add the DoPE moduleRPM-Net · ModelNet40 full+cleanMAE(R) degrees: 0.028 -> 0.0009Improved
add the DoPE moduleDeepGMR · ModelNet40 full+cleanMAE(R) degrees: 0.0008 -> 0.0002Improved
add the DoPE moduleDCP · ModelNet40 full+noisyMAE(R) degrees: 4.528 -> 1.6240Improved
add the DoPE modulePRNet · ModelNet40 partial+cleanMAE(R) degrees: 1.454 -> 0.311634Improved
add the DoPE moduleIDAM · ModelNet40 partial+noisyMAE(R) degrees: 1.85 -> 0.423182Improved
add the DoPE moduleDCP · ScanObjectNNMAE(R) degrees: 5.749913 -> 1.731377Improved
add the DoPE moduleDGR · 3DMatchrecall (%): 91.3% -> 96.6%Improved
add local attention (ablation)DCP · ModelNet40 full+noisyMAE(R) degrees: 5.34 -> 4.74Improved
add non-local attention (ablation)DCP · ModelNet40 full+noisyMAE(R) degrees: 5.34 -> 4.45Improved
compute positional embeddings w.r.t. joint origin instead of individual origin with non-local attention (ablation)DoPE** · ModelNet40 full+noisyMAE(R) degrees: 3.86 -> 0.80Improved
compute positional embeddings w.r.t. joint origin instead of individual origin with local attention (ablation)DoPE* · ModelNet40 full+noisyMAE(R) degrees: 2.38 -> 1.04Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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