Line Segment Detection Papers

A collection of line segment detection papers (a.k.a. wireframe parsing).

Outline

• Deep-Learning Based Approaches
  • Line Segment Detection
  • Wireframe Parsing
• Traditional approaches
• Datasets

1. Deep-Learning Based Approaches

1.1 Line Segment Detection

Name	Paper	Source	Code/Project
LaRecNet	Learning to Calibrate Straight Lines for Fisheye Image Rectification	CVPR 2019	[Project]
PPGNet	PPGNet: Learning Point-Pair Graph for Line Segment Detection	CVPR 2019	[Code]
AFM	Learning Attraction Field Representation for Robust Line Segment Detection	CVPR 2019	[Code]
Linelet	A Novel Linelet-based Representation for Line Segment Detection.	IPAMI 2017	[Code]

1.2 Wireframe Parsing

Name	Paper	Source	Code/Project
HAWP	Holistically-Attracted Wireframe Parsing	CVPR 2020	[Code]
	Learning to Reconstruct 3D Manhattan Wireframes from a Single Image	ICCV 2019	[Project]
LCNN	End-to-End Wireframe Parsing	ICCV 2019	[Code]
Wireframe	Learning to Parse Wireframes in Images of Man-Made Environments	CVPR 2018	[Code]

---

2. Traditional Approaches

Name	Paper	Source	Code/Project
MCMLSD	MCMLSD: A Probabilistic Algorithm and Evaluation Framework for Line Segment Detection	TPAMI 2020
MCMLSD	MCMLSD: A Dynamic Programming Approach to Line Segment Detection	CVPR 2017	[Code]
CannyLines	Cannylines: A parameter-free line segment detector	ICIP 2015	[Project]
	Accurate and robust line segment extraction using minimum entropy with hough transform	TIP 2015
	Lifting 3D manhattan lines from a single image	ICCV 2013
LSD	LSD: A Fast Line Segment Detector with a False Detection Control	TPAMI 2010	[Code]
PPHT	Robustdetection of lines using the progressive probabilistic hough transform	CVIU 2000
	Generalizing the hough transform to detect arbitrary shapes	PR 1981

---

3. Datasets

• Wireframe Dataset
• YorkUrbanDB (York Urban Line Segment Database)