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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Apply ASG rather than AMAT with histogram cost | Unsupervised medial axis extraction · BMAX500 test, half resolution, single-annotation evaluation | F1: .380 -> .435 | Improved |
| Apply ASG rather than AMAT with histogram cost | Unsupervised medial axis extraction · BMAX500 test, full resolution, single-annotation evaluation | F1: .431 -> .507 | Improved |
| Apply ASG rather than AMAT with histogram cost | Unsupervised medial axis extraction · BMAX500 test, half resolution | runtime: 33.7 -> 6.5 | Improved |
| Apply ASG rather than AMAT with histogram cost | Unsupervised medial axis extraction · BMAX500 test, full resolution | runtime: 393.2 -> 34.7 | Improved |
| Use histogram cost instead of color cost (ablation) | AMAT · BMAX500 test, half resolution, standard evaluation | F1: .487 -> .509 | Improved |
| Use histogram cost instead of color cost (ablation) | ASG · BMAX500 test, half resolution, standard evaluation | F1: .422 -> .522 | Improved |
| Use the single-annotation protocol rather than standard multi-annotation evaluation | BMAX500 evaluation · BMAX500, half resolution | F1: AMAT (Hist): .509 -> .380; ASG (Hist): .522 -> .435 | Mixed |
| Use the single-annotation protocol rather than standard multi-annotation evaluation | BMAX500 evaluation · BMAX500, full resolution | F1: AMAT (Hist): .584 -> .431; ASG (Hist): .564 -> .507 | Mixed |
| Apply ASG rather than AMAT | Unsupervised medial axis extraction · SK-LARGE test | F1: .509 -> .511 | Improved |
| Apply ASG rather than AMAT | Unsupervised medial axis extraction · SK-LARGE test | runtime: 511.9 -> 63.2 | Improved |
Closest papers by meaning
- AMAT: Medial Axis Transform for Natural Images (ICCV 2017 · similarity 0.87)
- Neural Atlas Graphs for Dynamic Scene Decomposition and Editing (NeurIPS 2025 · similarity 0.83)
- FastJAM: a Fast Joint Alignment Model for Images (NeurIPS 2025 · similarity 0.83)
- VideoSPatS: Video SPatiotemporal Splines for Disentangled Occlusion, Appearance and Motion Modeling and Editing (CVPR 2025 · similarity 0.82)
- HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding (CVPR 2024 · similarity 0.82)
- Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures (CVPR 2025 · similarity 0.81)
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.
