Research map / Detection and segmentation / CNN features
Fast Detection of Curved Edges at Low SNR
Nati Ofir, Meirav Galun, Boaz Nadler, Ronen Basri
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 |
|---|---|---|---|
| Use the O(N^{1.5}) beam-curve detector instead of Canny | Curved-edge detection · Simulations, SNR 0.6-1.0 | F-score: 0.24 -> 0.47 | Improved |
| Use the O(N^{1.5}) beam-curve detector instead of Canny | Curved-edge detection · Simulations, SNR 1.2-2.0 | F-score: 0.67 -> 0.75 | Improved |
| Use the O(N^{1.5}) beam-curve detector instead of Canny | Curved-edge detection · Simulations, SNR 2.2-2.6 | F-score: 0.85 -> 0.88 | Improved |
| Pre-denoise with BM3D before Canny | Canny edge detection · Simulations, SNR 0.6-1.0 | F-score: 0.24 -> 0.12 | Hurt |
| Pre-denoise with BM3D before Canny | Canny edge detection · Simulations, SNR 1.2-2.0 | F-score: 0.67 -> 0.67 | No clear effect |
| Pre-denoise with BM3D before Canny | Canny edge detection · Simulations, SNR 2.2-2.6 | F-score: 0.85 -> 0.84 | Hurt |
| Restrict each interface search to the best k pixels (ablation) | Beam-curve detector · Simulations, SNR 0.6-1.0 | F-score: 0.47 -> 0.46 | Hurt |
| Restrict each interface search to the best k pixels (ablation) | Beam-curve detector · Simulations, SNR 1.2-2.0 | F-score: 0.75 -> 0.72 | Hurt |
| Restrict each interface search to the best k pixels (ablation) | Beam-curve detector · Simulations, SNR 2.2-2.6 | F-score: 0.88 -> 0.87 | Hurt |
| Use the O(N^{1.5}) beam-curve detector instead of Alpert et al.'s method | Curved-edge detection · 63 artificial images | Average F-score: ≈ 0.74 -> ≈ 0.79 | Improved |
Closest papers by meaning
- On Detection of Faint Edges in Noisy Images (TPAMI 2019 · similarity 0.89)
- Field of Junctions: Extracting Boundary Structure at Low SNR (ICCV 2021 · similarity 0.87)
- DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection (AAAI 2024 · similarity 0.84)
- STAR-Edge: Structure-aware Local Spherical Curve Representation for Thin-walled Edge Extraction from Unstructured Point Clouds (CVPR 2025 · similarity 0.83)
- MuGE: Multiple Granularity Edge Detection (CVPR 2024 · similarity 0.81)
- Rethinking Boundary Discontinuity Problem for Oriented Object Detection (CVPR 2024 · 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.
