AI Paper Atlas

Research map / 3D vision / Face and shape

Learning an Effective Equivariant 3D Descriptor Without Supervision

Riccardo Spezialetti, Samuele Salti, Luigi Di Stefano

ICCV 2019 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 40 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
orient the equivariant descriptor with an external LRF (FLARE) instead of self-orienting (ablation)equivariant spherical CNN descriptor · 3DMatch averagerecall: 0.8918 -> 0.9420Improved
orient the equivariant descriptor with an external LRF instead of self-orienting (ablation)equivariant spherical CNN descriptor · Rotated 3DMatch averagerecall: 0.8778 -> 0.9387Improved
learn an equivariant descriptor then orient it, instead of learning an invariant one from PPF (PPFFoldNet)FoldingNet-style unsupervised descriptor · 3DMatch averagerecall: 0.7182 -> 0.9420Improved
learn equivariant descriptor instead of invariant CGFlearned descriptor · 3DMatch averagerecall: 0.4776 -> 0.9420Improved
use Spherical CNN encoder instead of PointNet to obtain rotation invariance after rotating the output (ablation)descriptor encoder · descriptor distance under input rotationinvarianceImproved
use equivariant bottleneck instead of invariant bottleneck (max pooling) (ablation)folding decoder reconstruction · local patch reconstruction after 10K iterationsreconstruction qualityImproved
rotate inputs of the benchmark randomly (rotated 3DMatch)Ours LRF · 3DMatch averagerecall: 0.9420 -> 0.9387No clear effect
rotate inputs of the benchmark randomly (rotated 3DMatch)3DMatch descriptor · 3DMatch averagerecall: 0.5726 -> 0.0113Hurt
rotate inputs of the benchmark randomly (rotated 3DMatch)PPFNet · 3DMatch averagerecall: 0.6231 -> 0.0026Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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