# Deep Hough-Transform Line Priors

arXiv: https://arxiv.org/abs/2007.09493 · HTML: https://mlsanity.com/paper/2007.09493/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2020.

## Built on by (most cited first, 30 of 44)

- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients](https://mlsanity.com/paper/2212.07766/) (2022)
- [SOLD2: Self-supervised Occlusion-aware Line Description and Detection](https://mlsanity.com/paper/2104.03362/) (2021)
- [Zero-Shot Day-Night Domain Adaptation with a Physics Prior](https://mlsanity.com/paper/2108.05137/) (2021)
- [Towards Light-weight and Real-time Line Segment Detection](https://mlsanity.com/paper/2106.00186/) (2021)
- [Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning](https://mlsanity.com/paper/2210.12971/) (2022)
- [Fully Convolutional Line Parsing](https://mlsanity.com/paper/2104.11207/) (2021)
- [Prior Knowledge Guided Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.08877/) (2022)
- [ELSD: Efficient Line Segment Detector and Descriptor](https://mlsanity.com/paper/2104.14205/) (2021)
- [Deep vanishing point detection: Geometric priors make dataset variations vanish](https://mlsanity.com/paper/2203.08586/) (2022)
- [3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform](https://mlsanity.com/paper/2207.09291/) (2022)
- [VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow](https://mlsanity.com/paper/2503.22328/) (2025)
- [LSDNet: Trainable Modification of LSD Algorithm for Real-Time Line Segment Detection](https://mlsanity.com/paper/2209.04642/) (2022)
- [Learning to Construct 3D Building Wireframes from 3D Line Clouds](https://mlsanity.com/paper/2208.11948/) (2022)
- [Generating 3D House Wireframes with Semantics](https://mlsanity.com/paper/2407.12267/) (2024)
- [Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image](https://mlsanity.com/paper/2104.07986/) (2021)
- [CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation](https://mlsanity.com/paper/2504.19174/) (2025)
- [Detecting Line Segments in Motion-blurred Images with Events](https://mlsanity.com/paper/2211.07365/) (2022)
- [A Comprehensive Review of Image Line Segment Detection and Description: Taxonomies, Comparisons, and Challenges](https://mlsanity.com/paper/2305.00264/) (2023)
- [Slicer Networks](https://mlsanity.com/paper/2401.09833/) (2024)
- [DT-LSD: Deformable Transformer-based Line Segment Detection](https://mlsanity.com/paper/2411.13005/) (2024)
- [Hole-robust Wireframe Detection](https://mlsanity.com/paper/2111.15064/) (2021)
- [A Reliable Online Method for Joint Estimation of Focal Length and Camera Rotation](https://mlsanity.com/paper/2207.12934/) (2022)
- [DeDA: Deep Directed Accumulator](https://mlsanity.com/paper/2303.08434/) (2023)
- [ScaleLSD: Scalable Deep Line Segment Detection Streamlined](https://mlsanity.com/paper/2506.09369/) (2025)
- [NeRD++: Improved 3D-mirror symmetry learning from a single image](https://mlsanity.com/paper/2112.12579/) (2021)
- [HoughLaneNet: Lane Detection with Deep Hough Transform and Dynamic Convolution](https://mlsanity.com/paper/2307.03494/) (2023)
- [Harmonious Semantic Line Detection via Maximal Weight Clique Selection](https://mlsanity.com/paper/2104.06903/) (2021)
- [Semi-supervised lane detection with Deep Hough Transform](https://mlsanity.com/paper/2106.05094/) (2021)
- [Fast and Interpretable 2D Homography Decomposition: Similarity-Kernel-Similarity and Affine-Core-Affine Transformations](https://mlsanity.com/paper/2402.18008/) (2024)

## Abstract (arXiv)

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.