AI Paper Atlas

Research map / 3D vision / Face and shape

ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids

Dinesh Jayaraman, Ruohan Gao, Kristen Grauman

ECCV 2018 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 14 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 relative (observer-aligned) viewgrid targets instead of canonical alignment (ablation)ShapeCodes · ModelNet seen viewgrid completionMSE x1000: 4.689 -> 3.718Improved
add relative (observer-aligned) viewgrid targets instead of canonical alignment (ablation)ShapeCodes · ModelNet unseen viewgrid completionMSE x1000: 10.440 -> 7.005Improved
add relative (observer-aligned) viewgrid targets instead of canonical alignment (ablation)ShapeCodes · ShapeNet unseen viewgrid completionMSE x1000: 9.021 -> 6.811Improved
use relative-aligned viewgrid features instead of canonical-alignment features (ablation)ShapeCodes · ModelNet unseen recognitionaccuracy (%): 69.6 -> 71.2Improved
use relative-aligned viewgrid features instead of canonical-alignment features (ablation)ShapeCodes · ShapeNet seen recognitionaccuracy (%): 56.9 -> 57.7Improved
replace egomotion pair prediction with full viewgrid predictionShapeCodes · ModelNet seen recognitionaccuracy (%): 56.1 -> 65.2Improved
replace egomotion pair prediction with full viewgrid predictionShapeCodes · ShapeNet unseen recognitionaccuracy (%): 49.7 -> 54.8Improved
replace autoencoder (reconstruct own view) with viewgrid predictionShapeCodes · ModelNet seen recognitionaccuracy (%): 52.5 -> 65.2Improved
replace context inpainting with viewgrid predictionShapeCodes · ShapeNet seen recognitionaccuracy (%): 46.2 -> 57.7Improved
replace explicit voxel (3D-R2N2) encoder with implicit viewgrid encoderShapeCodes · ModelNet seen recognitionaccuracy (%): 49.4 -> 65.2Improved
replace point-cloud (PointSetNet) encoder with implicit viewgrid encoderShapeCodes · ModelNet seen recognitionaccuracy (%): 35.5 -> 65.2Improved
self-supervised ShapeCode instead of ImageNet-supervised VGGShapeCodes · ModelNet unseen recognitionaccuracy (%): 64.9 -> 71.2Improved

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