AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Cycle4Completion: Unpaired Point Cloud Completion Using Cycle Transformation With Missing Region Coding

Xin Wen, Zhizhong Han, Yan-Pei Cao, Pengfei Wan, Wen Zheng, Yu-Shen Liu

CVPR 2021 · Point clouds › Shape and surface completion · approach: Point cloud completion networks · 118 citations (OpenAlex)

Check 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 bidirectional cycle transformation with missing region coding instead of Pcl2PclCycle4Completion · ShapeNet (3D-EPN split)per point Chamfer distance × 10^4: 17.4 -> 14.1Improved
Add partial matching loss (ablation)Cycle4Completion · ShapeNet, four categoriesper point Chamfer distance × 10^4: 23.7 -> 9.1Improved
Add adversarial discriminator and loss (ablation)Cycle4Completion · ShapeNet, four categoriesper point Chamfer distance × 10^4: 12.8 -> 9.1Improved
Add cycle matching loss (ablation)Cycle4Completion · ShapeNet, four categoriesper point Chamfer distance × 10^4: 10.4 -> 9.1Improved
Add missing region codes and code matching loss (ablation)Cycle4Completion · ShapeNet, four categoriesper point Chamfer distance × 10^4: 9.4 -> 9.1Improved
Increase input resolution from 256 to 2048 points (ablation)Cycle4Completion · ShapeNetCD × 10^4: 14.4 -> 9.1Improved
Update auto-encoder and transformation parameters together when applying cycle loss (ablation)Cycle4Completion · ShapeNet, four categoriesCD × 10^4: 9.1 -> 10.1Hurt
Update auto-encoder and transformation parameters together when applying generator loss (ablation)Cycle4Completion · ShapeNet, four categoriescompletion outcomeHurt
Update auto-encoder and transformation parameters together when applying partial matching loss (ablation)Cycle4Completion · ShapeNet, four categoriescompletion outcomeHurt
Increase partial matching weight from 0.1 to 1.0 with cycle weight 0.01 (ablation)Cycle4Completion · ShapeNet carCD × 10^4: 9.8 -> 7.5Improved
Remove partial matching loss by setting its weight to 0 (ablation)Cycle4Completion · ShapeNet carCD × 10^4: 7.5 -> 17.1Hurt

Later papers that compared with this method

3 later accepted papers report Cycle4Completion as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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