# SOLD2: Self-supervised Occlusion-aware Line Description and Detection

arXiv: https://arxiv.org/abs/2104.03362 · HTML: https://mlsanity.com/paper/2104.03362/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 69 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [R2D2: Repeatable and Reliable Detector and Descriptor](https://mlsanity.com/paper/1906.06195/) (2019)
- [Non-Local Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2007.10042/) (2020)
- [Understanding the Limitations of CNN-based Absolute Camera Pose Regression](https://mlsanity.com/paper/1903.07504/) (2019)
- [ASLFeat: Learning Local Features of Accurate Shape and Localization](https://mlsanity.com/paper/2003.10071/) (2020)
- [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)
- [Semantic Visual Localization](https://mlsanity.com/paper/1712.05773/) (2017)
- [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)
- [PPGNet: Learning Point-Pair Graph for Line Segment Detection](https://mlsanity.com/paper/1905.03415/) (2019)
- [Learning to Reconstruct 3D Manhattan Wireframes from a Single Image](https://mlsanity.com/paper/1905.07482/) (2019)
- [D2D: Keypoint Extraction with Describe to Detect Approach](https://mlsanity.com/paper/2005.13605/) (2020)
- [TP-LSD: Tri-Points Based Line Segment Detector](https://mlsanity.com/paper/2009.05505/) (2020)
- [UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptor](https://mlsanity.com/paper/1907.04011/) (2019)
- [UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description without Local Correspondence Supervision](https://mlsanity.com/paper/2001.07252/) (2020)
- [SEKD: Self-Evolving Keypoint Detection and Description](https://mlsanity.com/paper/2006.05077/) (2020)
- [Reducing Drift in Structure From Motion Using Extended Features](https://mlsanity.com/paper/2008.12295/) (2020)

## Built on by (most cited first, 30 of 47)

- [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://mlsanity.com/paper/2304.02008/) (2023)
- [DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching](https://mlsanity.com/paper/2308.08479/) (2023)
- [DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients](https://mlsanity.com/paper/2212.07766/) (2022)
- [3D Line Mapping Revisited](https://mlsanity.com/paper/2303.17504/) (2023)
- [Robust Incremental Structure-from-Motion with Hybrid Features](https://mlsanity.com/paper/2409.19811/) (2024)
- [Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning](https://mlsanity.com/paper/2210.12971/) (2022)
- [ELSED: Enhanced Line SEgment Drawing](https://mlsanity.com/paper/2108.03144/) (2021)
- [Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization](https://mlsanity.com/paper/2109.04753/) (2021)
- [Pose Refinement with Joint Optimization of Visual Points and Lines](https://mlsanity.com/paper/2110.03940/) (2021)
- [LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment](https://mlsanity.com/paper/2410.12269/) (2024)
- [NEAT: Distilling 3D Wireframes from Neural Attraction Fields](https://mlsanity.com/paper/2307.10206/) (2023)
- [3D Neural Edge Reconstruction](https://mlsanity.com/paper/2405.19295/) (2024)
- [Fully Geometric Panoramic Localization](https://mlsanity.com/paper/2403.19904/) (2024)
- [EdgeGaussians -- 3D Edge Mapping via Gaussian Splatting](https://mlsanity.com/paper/2409.12886/) (2024)
- [Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction](https://mlsanity.com/paper/2506.21401/) (2025)
- [Learning to Construct 3D Building Wireframes from 3D Line Clouds](https://mlsanity.com/paper/2208.11948/) (2022)
- [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)
- [Handbook on Leveraging Lines for Two-View Relative Pose Estimation](https://mlsanity.com/paper/2309.16040/) (2023)
- [SketchSplat: 3D Edge Reconstruction via Differentiable Multi-view Sketch Splatting](https://mlsanity.com/paper/2503.14786/) (2025)
- [ScaleLSD: Scalable Deep Line Segment Detection Streamlined](https://mlsanity.com/paper/2506.09369/) (2025)
- [SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud](https://mlsanity.com/paper/2208.01925/) (2022)
- [Robust Surgical Tool Tracking with Pixel-based Probabilities for Projected Geometric Primitives](https://mlsanity.com/paper/2403.04971/) (2024)
- [LF-PGVIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras using Points and Geodesic Segments](https://mlsanity.com/paper/2306.06663/) (2023)
- [Stereo Visual Odometry with Deep Learning-Based Point and Line Feature Matching using an Attention Graph Neural Network](https://mlsanity.com/paper/2308.01125/) (2023)
- [Fast and Interpretable 2D Homography Decomposition: Similarity-Kernel-Similarity and Affine-Core-Affine Transformations](https://mlsanity.com/paper/2402.18008/) (2024)
- [Representing 3D sparse map points and lines for camera relocalization](https://mlsanity.com/paper/2402.18011/) (2024)
- [Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model](https://mlsanity.com/paper/2502.16779/) (2025)
- [Towards Establishing Dense Correspondence on Multiview Coronary Angiography: From Point-to-Point to Curve-to-Curve Query Matching](https://mlsanity.com/paper/2312.11593/) (2023)
- [SuperEdge: Towards a Generalization Model for Self-Supervised Edge Detection](https://mlsanity.com/paper/2401.02313/) (2024)

## Abstract (arXiv)

Compared to feature point detection and description, detecting and matching line segments offer additional challenges. Yet, line features represent a promising complement to points for multi-view tasks. Lines are indeed well-defined by the image gradient, frequently appear even in poorly textured areas and offer robust structural cues. We thus hereby introduce the first joint detection and description of line segments in a single deep network. Thanks to a self-supervised training, our method does not require any annotated line labels and can therefore generalize to any dataset. Our detector offers repeatable and accurate localization of line segments in images, departing from the wireframe parsing approach. Leveraging the recent progresses in descriptor learning, our proposed line descriptor is highly discriminative, while remaining robust to viewpoint changes and occlusions. We evaluate our approach against previous line detection and description methods on several multi-view datasets created with homographic warps as well as real-world viewpoint changes. Our full pipeline yields higher repeatability, localization accuracy and matching metrics, and thus represents a first step to bridge the gap with learned feature points methods. Code and trained weights are available at https://github.com/cvg/SOLD2.