# Horizon Lines in the Wild

arXiv: https://arxiv.org/abs/1604.02129 · HTML: https://mlsanity.com/paper/1604.02129/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2016.

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

- [SPEC: Seeing People in the Wild with an Estimated Camera](https://mlsanity.com/paper/2110.00620/) (2021)
- [Perspective Fields for Single Image Camera Calibration](https://mlsanity.com/paper/2212.03239/) (2022)
- [CTRL-C: Camera calibration TRansformer with Line-Classification](https://mlsanity.com/paper/2109.02259/) (2021)
- [Deep Learning for Camera Calibration and Beyond: A Survey](https://mlsanity.com/paper/2303.10559/) (2023)
- [DepthCues: Evaluating Monocular Depth Perception in Large Vision Models](https://mlsanity.com/paper/2411.17385/) (2024)
- [Self-Supervised Camera Self-Calibration from Video](https://mlsanity.com/paper/2112.03325/) (2021)
- [A step towards understanding why classification helps regression](https://mlsanity.com/paper/2308.10603/) (2023)
- [PnLCalib: Sports Field Registration via Points and Lines Optimization](https://mlsanity.com/paper/2404.08401/) (2024)
- [Robust Image Ordinal Regression with Controllable Image Generation](https://mlsanity.com/paper/2305.04213/) (2023)
- [A Deep Perceptual Measure for Lens and Camera Calibration](https://mlsanity.com/paper/2208.12300/) (2022)
- [Camera Calibration through Camera Projection Loss](https://mlsanity.com/paper/2110.03479/) (2021)
- [Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching](https://mlsanity.com/paper/2203.15285/) (2022)
- [Harmonious Semantic Line Detection via Maximal Weight Clique Selection](https://mlsanity.com/paper/2104.06903/) (2021)
- [SensorX2car: Sensors-to-car calibration for autonomous driving in road scenarios](https://mlsanity.com/paper/2301.07279/) (2023)
- [SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries](https://mlsanity.com/paper/2409.15553/) (2024)
- [Camera Calibration through Geometric Constraints from Rotation and Projection Matrices](https://mlsanity.com/paper/2402.08437/) (2024)
- [GimbalDiffusion: Gravity-Aware Camera Control for Video Generation](https://mlsanity.com/paper/2512.09112/) (2025)
- [A Simple Approach to Image Tilt Correction with Self-Attention MobileNet for Smartphones](https://mlsanity.com/paper/2111.00398/) (2021)
- [Parameters, Properties, and Process: Conditional Neural Generation of Realistic SEM Imagery Towards ML-assisted Advanced Manufacturing](https://mlsanity.com/paper/2302.08495/) (2023)
- [Hinge-Wasserstein: Estimating Multimodal Aleatoric Uncertainty in Regression Tasks](https://mlsanity.com/paper/2306.00560/) (2023)
- [Semantic Line Combination Detector](https://mlsanity.com/paper/2404.18399/) (2024)
- [Typography-Based Monocular Distance Estimation Framework for Vehicle Safety Systems](https://mlsanity.com/paper/2603.22781/) (2026)
- [Physics-Grounded Monocular Vehicle Distance Estimation Using Standardized License Plate Typography](https://mlsanity.com/paper/2604.12239/) (2026)
- [Neural Camera Models](https://mlsanity.com/paper/2208.12903/) (2022)
- [Multi-task Learning for Camera Calibration](https://mlsanity.com/paper/2211.12432/) (2022)
- [Single image calibration using knowledge distillation approaches](https://mlsanity.com/paper/2212.02379/) (2022)
- [Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning](https://mlsanity.com/paper/2509.00465/) (2025)
- [Riemannian Dueling Optimization](https://mlsanity.com/paper/2603.00023/) (2026)
- [Forecasting Solar Energy Using a Single Image](https://mlsanity.com/paper/2604.21982/) (2026)
- [Breaking the Horizontal Prior: From Long-Tailed Orientation Bias to Roll-Robust Monocular Depth Estimation](https://mlsanity.com/paper/2608.00678/) (2026)

## Abstract (arXiv)

The horizon line is an important contextual attribute for a wide variety of image understanding tasks. As such, many methods have been proposed to estimate its location from a single image. These methods typically require the image to contain specific cues, such as vanishing points, coplanar circles, and regular textures, thus limiting their real-world applicability. We introduce a large, realistic evaluation dataset, Horizon Lines in the Wild (HLW), containing natural images with labeled horizon lines. Using this dataset, we investigate the application of convolutional neural networks for directly estimating the horizon line, without requiring any explicit geometric constraints or other special cues. An extensive evaluation shows that using our CNNs, either in isolation or in conjunction with a previous geometric approach, we achieve state-of-the-art results on the challenging HLW dataset and two existing benchmark datasets.