Research map / Detection and segmentation / Open-set and few-shot detection
A Comprehensive Review of Image Line Segment Detection and Description: Taxonomies, Comparisons, and Challenges
Xinyu Lin, Yingjie Zhou, Yipeng Liu, Ce Zhu
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 learning-based instead of local-based line segment detectors | line segment detection · HPatches, KADID-10k, RDNIM (repeatability) | repeatability | No clear effect |
| use global Hough-based instead of other detectors | line segment detection · eight detection datasets | repeatability and F1 | Hurt |
| use local-based or DeepLSD instead of other detectors | line segment detection · YorkUrban | F1 score | Improved |
| use learning-based detectors instead of non-learning detectors | line segment detection · Wireframe and YorkUrban | location and orientation error | Hurt |
| use learning-based descriptors instead of statistical-based descriptors | line segment description · HPatches, KADID-10k, RDNIM, VGGaffine | matching precision and recall | No clear effect |
| use binary instead of float line segment descriptors | line segment description · HPatches, KADID-10k, RDNIM, VGGaffine | matching precision and recall | No clear effect |
| use GlueStick matching with point information instead of other descriptors | line segment description · HPatches, KADID-10k, RDNIM, VGGaffine | matching precision and recall | Improved |
| use edge fitting-based CPU detectors instead of learning-based GPU detectors | line segment detection · Wireframe (runtime) | FPS: 357 -> 2 | Improved |
Closest papers by meaning
- Deep Hough Transform for Semantic Line Detection (ECCV 2020 · similarity 0.89)
- MCMLSD: A Dynamic Programming Approach to Line Segment Detection (CVPR 2017 · similarity 0.88)
- DeepLSD: Line Segment Detection and Refinement With Deep Image Gradients (CVPR 2023 · similarity 0.88)
- Learning Attraction Field Representation for Robust Line Segment Detection (CVPR 2019 · similarity 0.87)
- A Novel Linelet-Based Representation for Line Segment Detection (TPAMI 2017 · similarity 0.87)
- ScaleLSD: Scalable Deep Line Segment Detection Streamlined (CVPR 2025 · similarity 0.86)
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.
