AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Primitive-Based Shape Abstraction via Nonparametric Bayesian Inference

Yuwei Wu, Weixiao Liu, Sipu Ruan, Gregory S. Chirikjian

ECCV 2022 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 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 merging post-process (ablation)Ours · ShapeNet (mean)Chamfer-L1: 0.017 -> 0.021Hurt
add the merging post-process (ablation)Ours · ShapeNet (mean)IoU: 0.547 -> 0.526Hurt
add the merging post-process (ablation)Ours · ShapeNet cannumber of primitives: 13.6 -> 1.1Improved
add the merging post-process (ablation)Ours · ShapeNet chairnumber of primitives: 26.9 -> 13.6Improved
add the merging post-process (ablation)Ours · ShapeNet tablenumber of primitives: 25.1 -> 9.5Improved
replace learned SQs with nonparametric Gibbs-sampling abstractionOurs vs SQs · ShapeNet (mean)Chamfer-L1: 0.053 -> 0.021Improved
replace learned SQs with nonparametric Gibbs-sampling abstractionOurs vs SQs · ShapeNet (mean)IoU: 0.242 -> 0.526Improved
replace K-means clustering with nonparametric Gibbs-sampling abstractionOurs vs K-means · ShapeNet (mean)Chamfer-L1: 0.057 -> 0.021Improved
replace K-means clustering with nonparametric Gibbs-sampling abstractionOurs vs K-means · ShapeNet (mean)IoU: 0.410 -> 0.526Improved
replace learned SQs with nonparametric Gibbs-sampling abstractionOurs vs SQs · D-FAUSTChamfer-L1: 0.0473 -> 0.0335Improved
replace learned SQs with nonparametric Gibbs-sampling abstractionOurs vs SQs · D-FAUSTIoU: 0.7138 -> 0.7709Improved
replace learned SQs with nonparametric Gibbs-sampling abstractionOurs vs SQs · ShapeNet chairIoU: 0.269 -> 0.557Improved

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