AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Cascaded Refinement Network for Point Cloud Completion with Self-supervision

Xiaogang Wang, Marcelo H. Ang, Gimhee Lee

TPAMI 2021 · Point clouds › Shape and surface completion · approach: Point cloud completion networks · 52 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 partial reconstruction auto-encoder and self-supervised strategies (SCRN vs CRN)CRN · PCN datasetmean Chamfer Distance: 8.505 -> 8.291Improved
add partial reconstruction and self-supervision (SCRN vs CRN)CRN · ModelNetmean Chamfer Distance: 2.606 -> 2.472Improved
add partial reconstruction and self-supervision (SCRN vs CRN)CRN · Completion3Dmean Chamfer Distance: 9.21 -> 9.13Improved
train with CD-2 instead of CD-1 (ablation)CRN · PCN datasetmean Chamfer Distance: 8.868 -> 8.505Improved
add self-supervised strategies and unlabeled data with 10% labeledPCN · ModelNet semi-supervisedChamfer Distance: 6.520 -> 4.496Improved
add self-supervised strategies and unlabeled data with 10% labeledCRN · ModelNet semi-supervisedChamfer Distance: 4.291 -> 3.331Improved
add self-supervised strategies with 90% labeledCRN · ModelNet semi-supervisedChamfer Distance: 2.669 -> 2.433Improved
add mirroring operation (ablation)CRN baseline · ModelNet bedChamfer Distance: 6.523 -> 6.331Improved
add contraction-expansion unit (ablation)CRN baseline · ModelNet bedChamfer Distance: 6.523 -> 6.243Improved
add discriminator (ablation)CRN baseline · ModelNet bedChamfer Distance: 6.523 -> 6.181Improved
add resampling strategy alone (ablation)CRN · ModelNet 10% labeledChamfer Distance: 6.887 -> 4.838Improved
add MixUp alone (ablation)CRN · ModelNet 10% labeledChamfer Distance: 6.887 -> 6.050Improved

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