AI Paper Atlas

Research map / 3D vision / Face and shape

3D Shape Segmentation With Projective Convolutional Networks

Evangelos Kalogerakis, Melinos Averkiou, Subhransu Maji, Siddhartha Chaudhuri

CVPR 2017 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 395 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 ShapePFCN instead of ShapeBoost3D shape part segmentation · ShapeNetCoreDataset Avg. labeling accuracy: 81.2 -> 87.5Improved
use ShapePFCN instead of ShapeBoost3D shape part segmentation · PSB & COSEGDataset Avg. labeling accuracy: 84.2 -> 92.2Improved
use adaptive coverage-based viewpoints instead of fixed dodecahedron viewpoints (ablation)ShapePFCN · ShapeNetCoreDataset Avg. labeling accuracy: 86.2 -> 87.5Improved
train the FCN and CRF jointly instead of separately (ablation)ShapePFCN · ShapeNetCoreDataset Avg. labeling accuracy: 85.9 -> 87.5Improved
add the surface CRF pairwise terms rather than using only the unary term (ablation)ShapePFCN · ShapeNetCoreDataset Avg. labeling accuracy: 82.1 -> 87.5Improved
initialize the FCN from pretrained VGG instead of training from scratch (ablation)ShapePFCN · ShapeNetCoreDataset Avg. labeling accuracy: 85.7 -> 87.5Improved
add a rendered height-from-ground-plane input channel (ablation)ShapePFCN with consistently upright shapes · ShapeNetCore, uprightDataset Avg. labeling accuracy: 87.5 -> 88.8Improved
use depth images alone instead of shaded and depth images (ablation)ShapePFCN · ShapeNetCorelabeling accuracy: 2.5%Hurt
use average rather than maximum to aggregate projected view confidences (ablation)ShapePFCN projection layer · ShapeNetCorelabeling accuracy: about 1%Hurt

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