# Deep Hough Transform for Semantic Line Detection

arXiv: https://arxiv.org/abs/2003.04676 · HTML: https://mlsanity.com/paper/2003.04676/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Mar 2020.

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

- [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://mlsanity.com/paper/2304.02008/) (2023)
- [Global2Local: Efficient Structure Search for Video Action Segmentation](https://mlsanity.com/paper/2101.00910/) (2021)
- [Understanding 3D Object Articulation in Internet Videos](https://mlsanity.com/paper/2203.16531/) (2022)
- [Understanding 3D Object Interaction from a Single Image](https://mlsanity.com/paper/2305.09664/) (2023)
- [Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes](https://mlsanity.com/paper/2203.15302/) (2022)
- [DRAWER: Digital Reconstruction and Articulation With Environment Realism](https://mlsanity.com/paper/2504.15278/) (2025)
- [ContrastMask: Contrastive Learning to Segment Every Thing](https://mlsanity.com/paper/2203.09775/) (2022)
- [Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videos](https://mlsanity.com/paper/2504.07940/) (2025)
- [3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform](https://mlsanity.com/paper/2207.09291/) (2022)
- [RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks](https://mlsanity.com/paper/2206.06637/) (2022)
- [Learning to Construct 3D Building Wireframes from 3D Line Clouds](https://mlsanity.com/paper/2208.11948/) (2022)
- [Agronav: Autonomous Navigation Framework for Agricultural Robots and Vehicles using Semantic Segmentation and Semantic Line Detection](https://mlsanity.com/paper/2304.04333/) (2023)
- [Slicer Networks](https://mlsanity.com/paper/2401.09833/) (2024)
- [DeDA: Deep Directed Accumulator](https://mlsanity.com/paper/2303.08434/) (2023)
- [VibNet: Vibration-Boosted Needle Detection in Ultrasound Images](https://mlsanity.com/paper/2403.14523/) (2024)
- [MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness](https://mlsanity.com/paper/2505.20426/) (2025)
- [ScaleLSD: Scalable Deep Line Segment Detection Streamlined](https://mlsanity.com/paper/2506.09369/) (2025)
- [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)
- [Aesthetic Attribute Assessment of Images Numerically on Mixed Multi-attribute Datasets](https://mlsanity.com/paper/2207.01806/) (2022)
- [Predicting Scores of Various Aesthetic Attribute Sets by Learning from Overall Score Labels](https://mlsanity.com/paper/2312.03222/) (2023)
- [No More Ambiguity in 360deg Room Layout via Bi-Layout Estimation](https://mlsanity.com/paper/2404.09993/) (2024)
- [Multiple Object Tracking in Video SAR: A Benchmark and Tracking Baseline](https://mlsanity.com/paper/2506.12105/) (2025)
- [Efficient Surgical Robotic Instrument Pose Reconstruction in Real World Conditions Using Unified Feature Detection](https://mlsanity.com/paper/2510.03532/) (2025)
- [Computational Scaffolding of Composition, Value, and Color for Disciplined Drawing](https://mlsanity.com/paper/2509.17268/) (2025)
- [A Fast Horizon Detector and a New Annotated Dataset for Maritime Video Processing](https://mlsanity.com/paper/2110.13694/) (2021)
- [Semantic Line Combination Detector](https://mlsanity.com/paper/2404.18399/) (2024)
- [UniVector: Unified Vector Extraction via Instance-Geometry Interaction](https://mlsanity.com/paper/2510.13234/) (2025)
- [MiLSD: A Micro Line-Segment Detector for Resource-Constrained Devices](https://mlsanity.com/paper/2607.06600/) (2026)
- [DAGrid: Directed Accumulator Grid](https://mlsanity.com/paper/2306.02589/) (2023)

## Abstract (arXiv)

We focus on a fundamental task of detecting meaningful line structures, a.k.a. semantic line, in natural scenes. Many previous methods regard this problem as a special case of object detection and adjust existing object detectors for semantic line detection. However, these methods neglect the inherent characteristics of lines, leading to sub-optimal performance. Lines enjoy much simpler geometric property than complex objects and thus can be compactly parameterized by a few arguments. To better exploit the property of lines, in this paper, we incorporate the classical Hough transform technique into deeply learned representations and propose a one-shot end-to-end learning framework for line detection. By parameterizing lines with slopes and biases, we perform Hough transform to translate deep representations into the parametric domain, in which we perform line detection. Specifically, we aggregate features along candidate lines on the feature map plane and then assign the aggregated features to corresponding locations in the parametric domain. Consequently, the problem of detecting semantic lines in the spatial domain is transformed into spotting individual points in the parametric domain, making the post-processing steps, i.e. non-maximal suppression, more efficient. Furthermore, our method makes it easy to extract contextual line features eg features along lines close to a specific line, that are critical for accurate line detection. In addition to the proposed method, we design an evaluation metric to assess the quality of line detection and construct a large scale dataset for the line detection task. Experimental results on our proposed dataset and another public dataset demonstrate the advantages of our method over previous state-of-the-art alternatives.