AI Paper Atlas

Research map / 3D vision / Face and shape

Learning a Predictable and Generative Vector Representation for Objects

Rohit Girdhar, David F. Fouhey, Mikel Rodriguez, Abhinav Gupta

ECCV 2016 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 682 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 joint fine-tuning of the full TL network (ablation)TL-embedding network · ShapeNet CAD voxel predictionAverage AP: 62.7 -> 65.4Improved
add joint fine-tuning (ablation)TL-embedding network · ShapeNet CAD voxel prediction (Bed)AP: 33.8 -> 41.9Improved
add joint fine-tuning (ablation)TL-embedding network · ShapeNet CAD voxel prediction (Sofa)AP: 79.3 -> 79.3No clear effect
add joint fine-tuning (ablation)autoencoder · ShapeNet CAD reconstructionOverall AP: 97.6 -> 97.6No clear effect
predict 64-D embedding then decode instead of predicting voxels directly (Direct-conv4) (ablation)AlexNet image to voxel · ShapeNet CAD voxel predictionAverage AP: 38.0 -> 65.4Improved
predict embedding instead of voxels directly (Direct-fc8) (ablation)AlexNet image to voxel · ShapeNet CAD voxel predictionAverage AP: 24.8 -> 65.4Improved
predict embedding instead of voxels directly (ablation)AlexNet image to voxel · IKEA voxel predictionOverall AP: 31.1 -> 38.3Improved
remove translational alignment correction at evaluationTL-embedding network · IKEA voxel predictionAP: 33% vs 28%Improved
use convolutional autoencoder instead of PCA with same dimensions (ablation)voxel embedding · ShapeNet CAD reconstructionOverall AP: 96.8 -> 97.6Improved
use autoencoder embedding instead of PCA for classification (ablation)64D features + linear SVM · ModelNet40accuracy: 68.4% -> 74.4%Improved
use learned embedding retrieval instead of AlexNet fc7 nearest neighborCAD retrieval · IKEA CAD retrievalMean recall@10 overall: 19.4 -> 29.3Improved
use learned embedding retrieval instead of fc7 nearest neighborCAD retrieval · IKEA CAD retrieval (Table)Mean recall@10: 17.4 -> 8.0Hurt

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