atlas

Research map / 3D vision / Face and shape

LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery

NeurIPS 2022 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 15 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
use 2D-3D semantic consistency loss (ablation)LASSIE · Pascal-Part Horseoverall IOU: 65.3 -> 81.9Helped
use 2D-3D semantic consistency loss (ablation)LASSIE · Pascal-Part Cowpart transfer PCP: 60.3 -> 77.0Helped
use 2D-3D semantic consistency loss (ablation)LASSIE · Pascal-Part SheepPCK@0.1: 55.3 -> 70.8Helped
use primitive-shape prior MLP (ablation)LASSIE · Pascal-Part Horseoverall IOU: 81.0 -> 81.9Helped
use primitive-shape prior MLP (ablation)LASSIE · Pascal-Part Cowpart IOU: 33.7 -> 35.1Helped
use primitive-shape prior MLP (ablation)LASSIE · Pascal-Part SheepPCK@0.1: 68.9 -> 70.8Helped
initialize 3D feature assignment with heuristics instead of manual part-to-cluster mappingLASSIE · Pascal-Part HorsePCK@0.1: 73.0 -> 72.1Hurt

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