AI Paper Atlas

Research map / 3D vision / Face and shape

Elastic Shape Analysis of Tree-Like 3D Objects Using Extended SRVF Representation

Guan Wang, Hamid Laga, Anuj Srivastava

TPAMI 2023 · 3D vision › Face and shape · approach: Optimization-based shape matching · 8 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
use main-side branching elastic SRVF tree-shape space instead of the prior father-child tree-spacestatistical shape model of botanical trees · Botanical tree collection (6 examples)Information captured by top-1 eigenvalue: 0.54 -> 0.60Improved
use proposed framework instead of Wang et al. for top-3 eigenvaluesstatistical shape model of botanical trees · Botanical tree collection (6 examples)Information captured by top-3 eigenvalues: 0.92 -> 0.94Improved
use proposed framework instead of Wang et al. for top-4 eigenvaluesstatistical shape model of botanical trees · Botanical tree collection (6 examples)Information captured by top-4 eigenvalues: 0.97 -> 0.99Improved
use proposed framework with five eigenvaluesstatistical shape model of botanical trees · Botanical tree collection (6 examples)Information captured by top-5 eigenvalues: 1.00 -> 1.00No clear effect
add shape matching (graph matching) step before geodesic computation (ablation)tree geodesic computation · neuronal and botanical trees (qualitative)naturalness of geodesicsImproved
set lambda_s to 10^-4 (down-weight shape dissimilarity term) (ablation)tree metric weights · botanical tree geodesiccorrespondence behavior: lambda_s=10^-4Mixed
set lambda_p to 10^-4 (down-weight bifurcation point distance term) (ablation)tree metric weights · botanical tree geodesiccorrespondence behavior: lambda_p=10^-4Mixed
random initialization of correspondences across 10 runs (ablation)gradient-descent geodesic computation · Two botanical trees, 10 random initializationsgeodesic length: 32.4029 to 33.8112No 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