# Detecting Vanishing Points using Global Image Context in a Non-Manhattan World

arXiv: https://arxiv.org/abs/1608.05684 · HTML: https://mlsanity.com/paper/1608.05684/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2016.

## Built on by (most cited first, 27 of 27)

- [Perspective Fields for Single Image Camera Calibration](https://mlsanity.com/paper/2212.03239/) (2022)
- [Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors](https://mlsanity.com/paper/2503.17316/) (2025)
- [GeoCalib: Learning Single-image Calibration with Geometric Optimization](https://mlsanity.com/paper/2409.06704/) (2024)
- [Tame a Wild Camera: In-the-Wild Monocular Camera Calibration](https://mlsanity.com/paper/2306.10988/) (2023)
- [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)
- [Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation](https://mlsanity.com/paper/2510.08673/) (2025)
- [Deep vanishing point detection: Geometric priors make dataset variations vanish](https://mlsanity.com/paper/2203.08586/) (2022)
- [Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World](https://mlsanity.com/paper/2505.04788/) (2025)
- [PnLCalib: Sports Field Registration via Points and Lines Optimization](https://mlsanity.com/paper/2404.08401/) (2024)
- [Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction](https://mlsanity.com/paper/2308.10694/) (2023)
- [Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration](https://mlsanity.com/paper/2411.17240/) (2024)
- [PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus](https://mlsanity.com/paper/2401.14919/) (2024)
- [Camera Calibration through Camera Projection Loss](https://mlsanity.com/paper/2110.03479/) (2021)
- [MC-NeRF: Multi-Camera Neural Radiance Fields for Multi-Camera Image Acquisition Systems](https://mlsanity.com/paper/2309.07846/) (2023)
- [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)
- [Deep Single Image Camera Calibration by Heatmap Regression to Recover Fisheye Images Under Manhattan World Assumption](https://mlsanity.com/paper/2303.17166/) (2023)
- [SOFI: Multi-Scale Deformable Transformer for Camera Calibration with Enhanced Line Queries](https://mlsanity.com/paper/2409.15553/) (2024)
- [Surface Normal Clustering for Implicit Representation of Manhattan Scenes](https://mlsanity.com/paper/2212.01331/) (2022)
- [A Simple Approach to Image Tilt Correction with Self-Attention MobileNet for Smartphones](https://mlsanity.com/paper/2111.00398/) (2021)
- [Semantic Line Combination Detector](https://mlsanity.com/paper/2404.18399/) (2024)
- [Multi-task Learning for Camera Calibration](https://mlsanity.com/paper/2211.12432/) (2022)
- [GravCal: Single-Image Calibration of IMU Gravity Priors with Per-Sample Confidence](https://mlsanity.com/paper/2603.19654/) (2026)
- [Calibration-Free Vehicle Speed Estimation: A Monocular Keypoint-Template Approach](https://mlsanity.com/paper/2608.16785/) (2026)
- [Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States](https://mlsanity.com/paper/2609.04196/) (2026)

## Abstract (arXiv)

We propose a novel method for detecting horizontal vanishing points and the zenith vanishing point in man-made environments. The dominant trend in existing methods is to first find candidate vanishing points, then remove outliers by enforcing mutual orthogonality. Our method reverses this process: we propose a set of horizon line candidates and score each based on the vanishing points it contains. A key element of our approach is the use of global image context, extracted with a deep convolutional network, to constrain the set of candidates under consideration. Our method does not make a Manhattan-world assumption and can operate effectively on scenes with only a single horizontal vanishing point. We evaluate our approach on three benchmark datasets and achieve state-of-the-art performance on each. In addition, our approach is significantly faster than the previous best method.