AI Paper Atlas

Research map / 3D vision / Face and shape

Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly

Ruihai Wu, Chenrui Tie, Yushi Du, Yan Zhao, Hao Dong

ICCV 2023 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 20 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 part correlations to SE(3)-equivariant part representations (ablation)SE(3) shape assembly · Breaking Bad everydaypart accuracy (%): 18.4 -> 26.7Improved
add part correlations (ablation)SE(3) shape assembly · Geometric Shape Matingpart accuracy (%): 80.5 -> 85.7Improved
add translation embedding (ablation)SE(3) shape assembly · Breaking Bad everydaypart accuracy (%): 22.5 -> 26.7Improved
add translation embedding (ablation)SE(3) shape assembly · Geometric Shape Matingpart accuracy (%): 84.3 -> 85.7Improved
add adversarial learning (ablation)SE(3) shape assembly · Breaking Bad everydaypart accuracy (%): 23.7 -> 26.7Improved
add adversarial learning (ablation)SE(3) shape assembly · Geometric Shape Matingpart accuracy (%): 82.6 -> 85.7Improved
use SE(3)-equivariant method instead of NSMtwo-part mating · Geometric Shape MatingRMSE (R) degree: 21.3 -> 15.9Improved
add part correlations on translation (ablation)SE(3) shape assembly · Geometric Shape MatingRMSE (T) x10^-2: 2.9 -> 2.7No clear effect

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