# DT-LSD: Deformable Transformer-based Line Segment Detection

arXiv: https://arxiv.org/abs/2411.13005 · HTML: https://mlsanity.com/paper/2411.13005/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 20 Nov 2024.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [Line Segment Detection Using Transformers without Edges](https://mlsanity.com/paper/2101.01909/) (2021)
- [End-to-End Wireframe Parsing](https://mlsanity.com/paper/1905.03246/) (2019)
- [Learning to Parse Wireframes in Images of Man-Made Environments](https://mlsanity.com/paper/2007.07527/) (2020)
- [Holistically-Attracted Wireframe Parsing](https://mlsanity.com/paper/2003.01663/) (2020)
- [Learning Attraction Field Representation for Robust Line Segment Detection](https://mlsanity.com/paper/1812.02122/) (2018)
- [Deep Hough-Transform Line Priors](https://mlsanity.com/paper/2007.09493/) (2020)
- [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)
- [ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras](https://mlsanity.com/paper/2011.03174/) (2020)

## Built on by (most cited first, 6 of 6)

- [LINEA: Fast and Accurate Line Detection Using Scalable Transformers](https://mlsanity.com/paper/2505.16264/) (2025)
- [MiLSD: A Micro Line-Segment Detector for Resource-Constrained Devices](https://mlsanity.com/paper/2607.06600/) (2026)
- [Adaptive Dual-Constrained Line Aggregation for Cross-Paradigm Line Segment Detection](https://mlsanity.com/paper/2508.19742/) (2025)
- [SweepLSD: A One-Pass, O(width)-Memory Line Segment Detector with an Integer-Only Streaming Core and a Real-Time FPGA Realization](https://mlsanity.com/paper/2608.22086/) (2026)
- [STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation](https://mlsanity.com/paper/2608.29145/) (2026)
- [NPLSD: Accelerating Line-Segment Detection on NPU Microcontrollers](https://mlsanity.com/paper/2609.25022/) (2026)

## Abstract (arXiv)

Line segment detection is a fundamental low-level task in computer vision, and improvements in this task can impact more advanced methods that depend on it. Most new methods developed for line segment detection are based on Convolutional Neural Networks (CNNs). Our paper seeks to address challenges that prevent the wider adoption of transformer-based methods for line segment detection. More specifically, we introduce a new model called Deformable Transformer-based Line Segment Detection (DT-LSD) that supports cross-scale interactions and can be trained quickly. This work proposes a novel Deformable Transformer-based Line Segment Detector (DT-LSD) that addresses LETR's drawbacks. For faster training, we introduce Line Contrastive DeNoising (LCDN), a technique that stabilizes the one-to-one matching process and speeds up training by 34×. We show that DT-LSD is faster and more accurate than its predecessor transformer-based model (LETR) and outperforms all CNN-based models in terms of accuracy. In the Wireframe dataset, DT-LSD achieves 71.7 for sAP10 and 73.9 for sAP15; while 33.2 for sAP10 and 35.1 for sAP15 in the YorkUrban dataset.