Deep Hough-Transform Line Priors

Abstract

Classical work on line segment detection is knowledge-based; it uses carefully designed geometric priors using either image gradients, pixel groupings, or Hough transform variants. Instead, current deep learning methods do away with all prior knowledge and replace priors by training deep networks on large manually annotated datasets. Here, we reduce the dependency on labeled data by building on the classic knowledge-based priors while using deep networks to learn features. We add line priors through a trainable Hough transform block into a deep network. Hough transform provides the prior knowledge about global line parameterizations, while the convolutional layers can learn the local gradient-like line features. On the Wireframe (ShanghaiTech) and York Urban datasets we show that adding prior knowledge improves data efficiency as line priors no longer need to be learned from data. Keywords: Hough transform; global line prior, line segment detection.

arXiv commentECCV 2020, code online: https://github.com/yanconglin/Deep-Hough-Transform-Line-Priors

References in corpus (7)

• Do Deep Convolutional Nets Really Need to be Deep and Convolutional?
• Connectivity-Enforcing Hough Transform for the Robust Extraction of Line Segments
• HoughNet: neural network architecture for vanishing points detection
• Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields
• Exact and fast inversion of the approximate discrete Radon transform from partial data
• X-LineNet: Detecting Aircraft in Remote Sensing Images by a pair of Intersecting Line Segments
• Funnel Transform for Straight Line Detection