# NeurVPS: Neural Vanishing Point Scanning via Conic Convolution

arXiv: https://arxiv.org/abs/1910.06316 · HTML: https://mlsanity.com/paper/1910.06316/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2019.

## Built on by (most cited first, 24 of 24)

- [GeoCalib: Learning Single-image Calibration with Geometric Optimization](https://mlsanity.com/paper/2409.06704/) (2024)
- [Fully Convolutional Line Parsing](https://mlsanity.com/paper/2104.11207/) (2021)
- [Deep Learning for Camera Calibration and Beyond: A Survey](https://mlsanity.com/paper/2303.10559/) (2023)
- [NeRD: Neural 3D Reflection Symmetry Detector](https://mlsanity.com/paper/2105.03211/) (2021)
- [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)
- [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)
- [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)
- [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)
- [Ctrl123: Consistent Novel View Synthesis via Closed-Loop Transcription](https://mlsanity.com/paper/2403.10953/) (2024)
- [AlignDiff: Learning Physically-Grounded Camera Alignment via Diffusion](https://mlsanity.com/paper/2503.21581/) (2025)
- [Novel 3D Scene Understanding Applications From Recurrence in a Single Image](https://mlsanity.com/paper/2210.07991/) (2022)
- [Semantic Line Combination Detector](https://mlsanity.com/paper/2404.18399/) (2024)
- [VPOcc: Exploiting Vanishing Point for 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2408.03551/) (2024)
- [TopView: Vectorising road users in a bird's eye view from uncalibrated street-level imagery with deep learning](https://mlsanity.com/paper/2412.16229/) (2024)
- [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)
- [Camera Agnostic Two-Head Network for Ego-Lane Inference](https://mlsanity.com/paper/2404.12770/) (2024)

## Abstract (arXiv)

We present a simple yet effective end-to-end trainable deep network with geometry-inspired convolutional operators for detecting vanishing points in images. Traditional convolutional neural networks rely on aggregating edge features and do not have mechanisms to directly exploit the geometric properties of vanishing points as the intersections of parallel lines. In this work, we identify a canonical conic space in which the neural network can effectively compute the global geometric information of vanishing points locally, and we propose a novel operator named conic convolution that can be implemented as regular convolutions in this space. This new operator explicitly enforces feature extractions and aggregations along the structural lines and yet has the same number of parameters as the regular 2D convolution. Our extensive experiments on both synthetic and real-world datasets show that the proposed operator significantly improves the performance of vanishing point detection over traditional methods. The code and dataset have been made publicly available at https://github.com/zhou13/neurvps.