# Sports Camera Calibration via Synthetic Data

arXiv: https://arxiv.org/abs/1810.10658 · HTML: https://mlsanity.com/paper/1810.10658/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2018.

## Built on by (most cited first, 26 of 26)

- [Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting](https://mlsanity.com/paper/2104.09333/) (2021)
- [SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos](https://mlsanity.com/paper/2104.11452/) (2021)
- [DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations](https://mlsanity.com/paper/2208.08190/) (2022)
- [Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras](https://mlsanity.com/paper/2110.10355/) (2021)
- [TVCalib: Camera Calibration for Sports Field Registration in Soccer](https://mlsanity.com/paper/2207.11709/) (2022)
- [PnLCalib: Sports Field Registration via Points and Lines Optimization](https://mlsanity.com/paper/2404.08401/) (2024)
- [WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation](https://mlsanity.com/paper/2501.02771/) (2025)
- [Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration](https://mlsanity.com/paper/2304.04437/) (2023)
- [A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision](https://mlsanity.com/paper/2307.03353/) (2023)
- [Video-based Sequential Bayesian Homography Estimation for Soccer Field Registration](https://mlsanity.com/paper/2311.10361/) (2023)
- [Smart Director: An Event-Driven Directing System for Live Broadcasting](https://mlsanity.com/paper/2201.04024/) (2022)
- [OpenSTARLab: Open Approach for Spatio-Temporal Agent Data Analysis in Soccer](https://mlsanity.com/paper/2502.02785/) (2025)
- [Extraction of Positional Player Data from Broadcast Soccer Videos](https://mlsanity.com/paper/2110.11107/) (2021)
- [BroadTrack: Broadcast Camera Tracking for Soccer](https://mlsanity.com/paper/2412.01721/) (2024)
- [Evaluating Soccer Player: from Live Camera to Deep Reinforcement Learning](https://mlsanity.com/paper/2101.05388/) (2021)
- [Localization of Ice-Rink for Broadcast Hockey Videos](https://mlsanity.com/paper/2104.10847/) (2021)
- [KaliCalib: A Framework for Basketball Court Registration](https://mlsanity.com/paper/2209.07795/) (2022)
- [Rink-Agnostic Hockey Rink Registration](https://mlsanity.com/paper/2401.01003/) (2023)
- [Can Geometry Save Central Views for Sports Field Registration?](https://mlsanity.com/paper/2504.20052/) (2025)
- [A Synthetic Benchmarking Pipeline to Compare Camera Calibration Algorithms](https://mlsanity.com/paper/2307.01013/) (2023)
- [From Broadcast to Minimap: Achieving State-of-the-Art SoccerNet Game State Reconstruction](https://mlsanity.com/paper/2504.06357/) (2025)
- [Homography Estimation in Complex Topological Scenes](https://mlsanity.com/paper/2308.01086/) (2023)
- [ESC: Evolutionary Stitched Camera Calibration in the Wild](https://mlsanity.com/paper/2404.12694/) (2024)
- [PTZ-Calib: Robust Pan-Tilt-Zoom Camera Calibration](https://mlsanity.com/paper/2502.09075/) (2025)
- [SoccerSynth Field: enhancing field detection with synthetic data from virtual soccer simulator](https://mlsanity.com/paper/2503.13969/) (2025)
- [Multi-Camera Self-Calibration in Sports Motion Capture: Leveraging Human and Stick Poses](https://mlsanity.com/paper/2604.17567/) (2026)

## Abstract (arXiv)

Calibrating sports cameras is important for autonomous broadcasting and sports analysis. Here we propose a highly automatic method for calibrating sports cameras from a single image using synthetic data. First, we develop a novel camera pose engine. The camera pose engine has only three significant free parameters so that it can effectively generate a lot of camera poses and corresponding edge (i.e, field marking) images. Then, we learn compact deep features via a siamese network from paired edge image and camera pose and build a feature-pose database. After that, we use a novel two-GAN (generative adversarial network) model to detect field markings in real images. Finally, we query an initial camera pose from the feature-pose database and refine camera poses using truncated distance images. We evaluate our method on both synthetic and real data. Our method not only demonstrates the robustness on the synthetic data but also achieves the state-of-the-art accuracy on a standard soccer dataset and very high performance on a volleyball dataset.