Corpus ID: 230770384

Line Segment Detection Using Transformers without Edges

  title={Line Segment Detection Using Transformers without Edges},
  author={Yifan Xu and W. Xu and David Cheung and Zhuowen Tu},
In this paper, we present a holistically end-to-end algorithm for line segment detection with transformers that is post-processing and heuristics-guided intermediate processing (edge/junction/region detection) free. Our method, named LinE segment TRansformers (LETR), tackles the three main problems in this domain, namely edge element detection, perceptual grouping, and holistic inference by three highlights in detection transformers (DETR) including tokenized queries with integrated encoding… Expand

Figures and Tables from this paper


CannyLines: A parameter-free line segment detector
  • X. Lu, Jian Yao, K. Li, L. Li
  • Mathematics, Computer Science
  • 2015 IEEE International Conference on Image Processing (ICIP)
  • 2015
  • 42
  • PDF
PPGNet: Learning Point-Pair Graph for Line Segment Detection
  • 20
  • PDF
Holistically-Attracted Wireframe Parsing
  • Nan Xue, Tianfu Wu, +4 authors P. Torr
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
  • 11
  • Highly Influential
  • PDF
End-to-End Wireframe Parsing
  • Yichao Zhou, Haozhi Qi, Y. Ma
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
  • 31
  • Highly Influential
  • PDF
Learning Attraction Field Representation for Robust Line Segment Detection
  • 31
  • PDF
Learning to Parse Wireframes in Images of Man-Made Environments
  • 52
  • Highly Influential
  • PDF
Dual Attention Network for Scene Segmentation
  • 859
  • PDF
Line segment detection using weighted mean shift procedures on a 2D slice sampling strategy
  • 33
Token-based extraction of straight lines
  • 176
Accurate and robust line segment extraction by analyzing distribution around peaks in Hough space
  • 91