Research map / Detection and segmentation / CNN features
On Detection of Faint Edges in Noisy Images
Nati Ofir, Meirav Galun, Sharon Alpert, Achi Brandt, Boaz Nadler, Ronen Basri
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 |
|---|---|---|---|
| use curve detector O(N^1.5) instead of Canny | edge detection · Simulated noisy shapes, SNR 1.0-1.6 | F-measure: 0.57 -> 0.73 | Improved |
| use curve detector O(N^1.5) instead of Canny | edge detection · Simulated noisy shapes, SNR 1.8-2.0 | F-measure: 0.71 -> 0.85 | Improved |
| use curve detector O(N^1.5) instead of Canny | edge detection · Simulated noisy shapes, SNR 0.0-0.8 | F-measure: 0.11 -> 0.14 | Improved |
| use O(N^1.5) curves instead of faster O(N log N) curves | Curves detector · Simulated noisy shapes, SNR 1.0-1.6 | F-measure: 0.7 -> 0.73 | Improved |
| use curved instead of straight edge detector | Our detectors · Simulated noisy shapes, SNR 1.0-1.6 | F-measure: 0.63 -> 0.73 | Improved |
| use our curves instead of state-of-the-art natural image boundary detector SE | edge detection · Simulated noisy shapes, SNR 1.8-2.0 | F-measure: 0.14 -> 0.85 | Improved |
| add BM3D denoising before Canny | Canny · Simulated noisy shapes, SNR 0.0-0.8 | F-measure: 0.11 -> 0.04 | Mixed |
| add BM3D denoising before Canny | Canny · Simulated noisy shapes, SNR 1.8-2.0 | F-measure: 0.71 -> 0.75 | Mixed |
Closest papers by meaning
- Fast Detection of Curved Edges at Low SNR (CVPR 2016 · similarity 0.89)
- DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection (AAAI 2024 · similarity 0.86)
- Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries (CVPR 2025 · similarity 0.83)
- MuGE: Multiple Granularity Edge Detection (CVPR 2024 · similarity 0.82)
- SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection (AAAI 2025 · similarity 0.81)
- STAR-Edge: Structure-aware Local Spherical Curve Representation for Thin-walled Edge Extraction from Unstructured Point Clouds (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.
