AI Paper Atlas

Research map / 3D vision / Face and shape

From Images to 3D Shape Attributes

David F. Fouhey, Abhinav Gupta, Andrew Zisserman

TPAMI 2017 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 8 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
switch base representation from VGG-M to VGG-163D shape attribute network · Sculptures testmean AUROC: 72.3 -> 74.4Improved
evaluate only on most confident predictions (top and bottom 25%)attribute network · Sculptures testmean AUROC: 72.3 -> 77.9Improved
evaluate only on top and bottom 10% of predictionsattribute network · Sculptures testmean AUROC: 72.3 -> 82.6Improved
add the shape embedding loss to attribute-only training (ablation)attribute network · Mental rotation (Easy)AUROC: +3.4% over best baseline (easy), +6.9% (hard)Improved
train attribute loss on top of pretrained weights (attribute-only vs pretrained) (ablation)attribute-only network · Mental rotationAUROC: +0.9% easy, +2.5% hardImproved
use 12D attributes instead of IFV representationattribute representation · Mental rotationAUROC: 3-4% betterImproved
vary shading cue only vs contour cue only on a sphere/cube (ablation)attribute network · synthetic planarity probecorrelation r_s: 0.96 and 0.97 (varying shading) vs 0.50 and 0.36 (varying contour)Mixed
replace FC layers with global average pooling (CAM network) (ablation)attribute network · Sculptures testmean AUROC: 0.64% lowerNo clear effect
clean metadata (reassign works)mental rotation evaluation · Mental rotationAUROC: about 0.1% increaseNo clear effect
use direct holistic attribute prediction instead of depth-then-attribute baselinesattribute network · Sculptures testmean AUROC: 62.5 -> 72.3Improved

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