AI Paper Atlas

Research map / 3D vision / 3D generation

3D CoMPaT: Composition of Materials on Parts of 3D Things

Yuchen Li, Ujjwal Upadhyay, Habib Slim, Tezuesh Varshney, Ahmed Abdelreheem, Arpit Prajapati, Suhail Pothigara, Peter Wonka, Mohamed Elhoseiny

ECCV 2022 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 15 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 a separate 2D shape classifier to 2D GCR-SEG (BPNet)2D GCR-SEG (BPNet) · 3D CoMPaT GCR (Top-1 predicted shape)Value-all: 3.54 -> 16.57Improved
add a separate 3D shape classifier (PCT) to 3D GCR-SEG (BPNet)3D GCR-SEG (BPNet) · 3D CoMPaT GCR (Top-1 predicted shape)Value-all: 2.02 -> 8.12Improved
add a separate 3D shape classifier to 3D GCR-SEG (BPNet)3D GCR-SEG (BPNet) · 3D CoMPaT GCR (Top-1 predicted shape)Shape accuracy: 36.91 -> 67.53Improved
provide ground truth parts instead of predicted parts (ablation)2D GCR-SEG (BPNet) + separate 2D shape classifier · 3D CoMPaT GCR (Top-1 predicted shape)Value-all: 16.57 -> 46.58Improved
provide ground truth materials instead of predicted materials (ablation)2D GCR-SEG (BPNet) + separate 2D shape classifier · 3D CoMPaT GCR (Top-1 predicted shape)Value: 40.39 -> 42.98Improved
provide ground truth materials instead of predicted materials (ablation)2D GCR-SEG (BPNet) + separate 2D shape classifier · 3D CoMPaT GCR (Top-1 predicted shape)Value-all: 16.57 -> 16.57No clear effect
provide ground truth parts instead of predicted parts (ablation)3D GCR-SEG (BPNet) + separate 3D shape classifier · 3D CoMPaT GCR (Top-1 predicted shape)Value-all: 8.12 -> 42.42Improved
train PointMLP on 3DCoMPaT (one composition per shape) instead of ModelNet40PointMLP · ScanObjectNN hardest variant (9 classes)accuracy: 24.33 -> 29.21Improved
replace PointNet++ with PCT for 3D part classification3D part classification · 3D CoMPaT 3D part classificationaccuracy: 24.18% -> 37.37%Improved
replace PointNet++ with PCT for 3D shape classification3D shape classification · 3D CoMPaT 3D shape classificationaccuracy: 57.95% -> 69.09%Improved

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