Research map / Graph learning / Graph algorithms and clustering
Reconstructing Curvilinear Networks Using Path Classifiers and Integer Programming
Engin Türetken, Fethallah Benmansour, Bjoern Andres, Przemysław Głowacki, Hanspeter Pfister, Pascal Fua
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 changed | Where | Measured | Effect |
|---|---|---|---|
| allow loops (Loopy-IP vs Arbor-IP) at low z-resolution (ablation) | Arbor-IP · Brainbow BRBW1 | DIADEM score: 0.44 -> 0.65 | Improved |
| allow loops (Loopy-IP vs Arbor-IP) at low z-resolution (ablation) | Arbor-IP · Brightfield BRF1 | DIADEM score: 0.59 -> 0.76 | Improved |
| allow loops (Loopy-IP vs Arbor-IP) at low z-resolution (ablation) | Arbor-IP · Brainbow BRBW2 | DIADEM score: 0.32 -> 0.56 | Improved |
| allow loops at high z-resolution (ablation) | Arbor-IP · Confocal-Axons OPF4 | DIADEM score: 0.89 -> 0.91 | No clear effect |
| use integer programming with path classifier instead of MST (ablation) | MST+PC · Brainbow BRBW1 | DIADEM score: 0.46 -> 0.65 | Improved |
| add path classifier to kMST (ablation) | kMST · Brainbow BRBW1 | DIADEM score: 0.26 -> 0.51 | Improved |
| add path classifier to kMST (ablation) | kMST · Brightfield BRF1 | DIADEM score: 0.51 -> 0.49 | Hurt |
| use subset formulation with lazy constraints instead of network flow | Network Flow · Brainbow BRBW1 | run time (minutes): 166.7 -> 32.9 | Improved |
| use subset formulation with lazy constraints instead of network flow | Network Flow · Brightfield BRF1 | run time (minutes): 379.3 -> 36.6 | Improved |
| use subset formulation with lazy constraints instead of network flow | Network Flow · Brightfield BRF2 | run time (minutes): 4.9 -> 7.7 | Hurt |
Closest papers by meaning
- Joint Segmentation and Path Classification of Curvilinear Structures (TPAMI 2019 · similarity 0.93)
- Active Learning for Delineation of Curvilinear Structures (CVPR 2016 · similarity 0.88)
- Promoting Connectivity of Network-Like Structures by Enforcing Region Separation (TPAMI 2021 · similarity 0.87)
- RoadTracer: Automatic Extraction of Road Networks From Aerial Images (CVPR 2018 · similarity 0.86)
- DeepBranchTracer: A Generally-Applicable Approach to Curvilinear Structure Reconstruction Using Multi-Feature Learning (AAAI 2024 · similarity 0.86)
- Patched Line Segment Learning for Vector Road Mapping (AAAI 2024 · similarity 0.84)
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.
