AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Appearance Shock Grammar for Fast Medial Axis Extraction From Real Images

Charles-Olivier Dufresne Camaro, Morteza Rezanejad, Stavros Tsogkas, Kaleem Siddiqi, Sven Dickinson

CVPR 2020 · Graph learning › Graph algorithms and clustering · approach: Graph embedding and spectral sparsification · 8 citations (OpenAlex)

Check 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
Apply ASG rather than AMAT with histogram costUnsupervised medial axis extraction · BMAX500 test, half resolution, single-annotation evaluationF1: .380 -> .435Improved
Apply ASG rather than AMAT with histogram costUnsupervised medial axis extraction · BMAX500 test, full resolution, single-annotation evaluationF1: .431 -> .507Improved
Apply ASG rather than AMAT with histogram costUnsupervised medial axis extraction · BMAX500 test, half resolutionruntime: 33.7 -> 6.5Improved
Apply ASG rather than AMAT with histogram costUnsupervised medial axis extraction · BMAX500 test, full resolutionruntime: 393.2 -> 34.7Improved
Use histogram cost instead of color cost (ablation)AMAT · BMAX500 test, half resolution, standard evaluationF1: .487 -> .509Improved
Use histogram cost instead of color cost (ablation)ASG · BMAX500 test, half resolution, standard evaluationF1: .422 -> .522Improved
Use the single-annotation protocol rather than standard multi-annotation evaluationBMAX500 evaluation · BMAX500, half resolutionF1: AMAT (Hist): .509 -> .380; ASG (Hist): .522 -> .435Mixed
Use the single-annotation protocol rather than standard multi-annotation evaluationBMAX500 evaluation · BMAX500, full resolutionF1: AMAT (Hist): .584 -> .431; ASG (Hist): .564 -> .507Mixed
Apply ASG rather than AMATUnsupervised medial axis extraction · SK-LARGE testF1: .509 -> .511Improved
Apply ASG rather than AMATUnsupervised medial axis extraction · SK-LARGE testruntime: 511.9 -> 63.2Improved

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