# Line Segment Detection Using Transformers without Edges

arXiv: https://arxiv.org/abs/2101.01909 · HTML: https://mlsanity.com/paper/2101.01909/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 6 Jan 2021.

## Builds on (most cited first, 17 of 17)

- [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)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Holistically-Nested Edge Detection](https://mlsanity.com/paper/1504.06375/) (2015)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [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)
- [PPGNet: Learning Point-Pair Graph for Line Segment Detection](https://mlsanity.com/paper/1905.03415/) (2019)

## Built on by (most cited first, 30 of 73)

- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [VectorMapNet: End-to-end Vectorized HD Map Learning](https://mlsanity.com/paper/2206.08920/) (2022)
- [DETRs with Hybrid Matching](https://mlsanity.com/paper/2207.13080/) (2022)
- [Text Spotting Transformers](https://mlsanity.com/paper/2204.01918/) (2022)
- [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://mlsanity.com/paper/2304.02008/) (2023)
- [DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients](https://mlsanity.com/paper/2212.07766/) (2022)
- [CRS-Diff: Controllable Remote Sensing Image Generation with Diffusion Model](https://mlsanity.com/paper/2403.11614/) (2024)
- [Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries](https://mlsanity.com/paper/2211.15658/) (2022)
- [TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network](https://mlsanity.com/paper/2108.03990/) (2021)
- [3D Line Mapping Revisited](https://mlsanity.com/paper/2303.17504/) (2023)
- [PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models](https://mlsanity.com/paper/2306.01461/) (2023)
- [Towards Light-weight and Real-time Line Segment Detection](https://mlsanity.com/paper/2106.00186/) (2021)
- [PlaneTR: Structure-Guided Transformers for 3D Plane Recovery](https://mlsanity.com/paper/2107.13108/) (2021)
- [CTRL-C: Camera calibration TRansformer with Line-Classification](https://mlsanity.com/paper/2109.02259/) (2021)
- [Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries](https://mlsanity.com/paper/2105.02170/) (2021)
- [HEAT: Holistic Edge Attention Transformer for Structured Reconstruction](https://mlsanity.com/paper/2111.15143/) (2021)
- [RNGDet: Road Network Graph Detection by Transformer in Aerial Images](https://mlsanity.com/paper/2202.07824/) (2022)
- [Glass Segmentation with RGB-Thermal Image Pairs](https://mlsanity.com/paper/2204.05453/) (2022)
- [Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning](https://mlsanity.com/paper/2210.12971/) (2022)
- [Laneformer: Object-aware Row-Column Transformers for Lane Detection](https://mlsanity.com/paper/2203.09830/) (2022)
- [Fully Convolutional Line Parsing](https://mlsanity.com/paper/2104.11207/) (2021)
- [RNGDet++: Road Network Graph Detection by Transformer with Instance Segmentation and Multi-scale Features Enhancement](https://mlsanity.com/paper/2209.10150/) (2022)
- [ELSED: Enhanced Line SEgment Drawing](https://mlsanity.com/paper/2108.03144/) (2021)
- [HSIGene: A Foundation Model For Hyperspectral Image Generation](https://mlsanity.com/paper/2409.12470/) (2024)
- [ELSD: Efficient Line Segment Detector and Descriptor](https://mlsanity.com/paper/2104.14205/) (2021)
- [Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives](https://mlsanity.com/paper/2505.14361/) (2025)
- [ScalableMap: Scalable Map Learning for Online Long-Range Vectorized HD Map Construction](https://mlsanity.com/paper/2310.13378/) (2023)
- [Pose Refinement with Joint Optimization of Visual Points and Lines](https://mlsanity.com/paper/2110.03940/) (2021)
- [HoW-3D: Holistic 3D Wireframe Perception from a Single Image](https://mlsanity.com/paper/2208.06999/) (2022)
- [EdgeGaussians -- 3D Edge Mapping via Gaussian Splatting](https://mlsanity.com/paper/2409.12886/) (2024)

## Abstract (arXiv)

In this paper, we present a joint end-to-end line segment detection algorithm using Transformers that is post-processing and heuristics-guided intermediate processing (edge/junction/region detection) free. Our method, named LinE segment TRansformers (LETR), takes advantages of having integrated tokenized queries, a self-attention mechanism, and an encoding-decoding strategy within Transformers by skipping standard heuristic designs for the edge element detection and perceptual grouping processes. We equip Transformers with a multi-scale encoder/decoder strategy to perform fine-grained line segment detection under a direct endpoint distance loss. This loss term is particularly suitable for detecting geometric structures such as line segments that are not conveniently represented by the standard bounding box representations. The Transformers learn to gradually refine line segments through layers of self-attention. In our experiments, we show state-of-the-art results on Wireframe and YorkUrban benchmarks.