# Deep vanishing point detection: Geometric priors make dataset variations vanish

arXiv: https://arxiv.org/abs/2203.08586 · HTML: https://mlsanity.com/paper/2203.08586/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 72 references that are in the map.
- First posted on arXiv 16 Mar 2022.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [Efficient parametrization of multi-domain deep neural networks](https://mlsanity.com/paper/1803.10082/) (2018)
- [VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition](https://mlsanity.com/paper/1710.06288/) (2017)
- [Zero-Shot Day-Night Domain Adaptation with a Physics Prior](https://mlsanity.com/paper/2108.05137/) (2021)
- [Deep Hough-Transform Line Priors](https://mlsanity.com/paper/2007.09493/) (2020)
- [Zero-Shot Deep Domain Adaptation](https://mlsanity.com/paper/1707.01922/) (2017)
- [Learning to Reconstruct 3D Manhattan Wireframes from a Single Image](https://mlsanity.com/paper/1905.07482/) (2019)
- [CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus](https://mlsanity.com/paper/2001.02643/) (2020)
- [Detecting Vanishing Points using Global Image Context in a Non-Manhattan World](https://mlsanity.com/paper/1608.05684/) (2016)
- [NeurVPS: Neural Vanishing Point Scanning via Conic Convolution](https://mlsanity.com/paper/1910.06316/) (2019)
- [Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation](https://mlsanity.com/paper/1703.01461/) (2017)
- [Efficient Multi-Domain Network Learning by Covariance Normalization](https://mlsanity.com/paper/1906.10267/) (2019)
- [Detecting Dominant Vanishing Points in Natural Scenes with Application to Composition-Sensitive Image Retrieval](https://mlsanity.com/paper/1608.04267/) (2016)
- [Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection](https://mlsanity.com/paper/1707.02427/) (2017)
- [Vanishing point detection with convolutional neural networks](https://mlsanity.com/paper/1609.00967/) (2016)

## Built on by (most cited first, 18 of 18)

- [Deep Learning for Camera Calibration and Beyond: A Survey](https://mlsanity.com/paper/2303.10559/) (2023)
- [Enhancing Diffusion Models with 3D Perspective Geometry Constraints](https://mlsanity.com/paper/2312.00944/) (2023)
- [Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World](https://mlsanity.com/paper/2505.04788/) (2025)
- [Curved Diffusion: A Generative Model With Optical Geometry Control](https://mlsanity.com/paper/2311.17609/) (2023)
- [VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow](https://mlsanity.com/paper/2503.22328/) (2025)
- [Deep Rotation Correction without Angle Prior](https://mlsanity.com/paper/2207.03054/) (2022)
- [PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus](https://mlsanity.com/paper/2401.14919/) (2024)
- [MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness](https://mlsanity.com/paper/2505.20426/) (2025)
- [SensorX2car: Sensors-to-car calibration for autonomous driving in road scenarios](https://mlsanity.com/paper/2301.07279/) (2023)
- [Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection](https://mlsanity.com/paper/2303.14311/) (2023)
- [Deep Single Image Camera Calibration by Heatmap Regression to Recover Fisheye Images Under Manhattan World Assumption](https://mlsanity.com/paper/2303.17166/) (2023)
- [Cross-Dimensional Refined Learning for Real-Time 3D Visual Perception from Monocular Video](https://mlsanity.com/paper/2303.09248/) (2023)
- [Recurrence-based Vanishing Point Detection](https://mlsanity.com/paper/2412.20666/) (2024)
- [ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points](https://mlsanity.com/paper/2512.07504/) (2025)
- [ElectricSight: 3D Hazard Monitoring for Power Lines Using Low-Cost Sensors](https://mlsanity.com/paper/2505.06573/) (2025)
- [FLIGHT: Fibonacci Lattice-based Inference for Geometric Heading in real-Time](https://mlsanity.com/paper/2602.23115/) (2026)
- [RVLoss: Runoff Vote Loss for Self-Supervised LiDAR Scene Flow Estimation](https://mlsanity.com/paper/2608.18864/) (2026)
- [Robust Multi-Model Fitting through Learning Neighbor Regions](https://mlsanity.com/paper/2609.15348/) (2026)

## Abstract (arXiv)

Deep learning has improved vanishing point detection in images. Yet, deep networks require expensive annotated datasets trained on costly hardware and do not generalize to even slightly different domains, and minor problem variants. Here, we address these issues by injecting deep vanishing point detection networks with prior knowledge. This prior knowledge no longer needs to be learned from data, saving valuable annotation efforts and compute, unlocking realistic few-sample scenarios, and reducing the impact of domain changes. Moreover, the interpretability of the priors allows to adapt deep networks to minor problem variations such as switching between Manhattan and non-Manhattan worlds. We seamlessly incorporate two geometric priors: (i) Hough Transform -- mapping image pixels to straight lines, and (ii) Gaussian sphere -- mapping lines to great circles whose intersections denote vanishing points. Experimentally, we ablate our choices and show comparable accuracy to existing models in the large-data setting. We validate our model's improved data efficiency, robustness to domain changes, adaptability to non-Manhattan settings.