# A Large Scale Homography Benchmark

arXiv: https://arxiv.org/abs/2302.09997 · HTML: https://mlsanity.com/paper/2302.09997/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 88 references that are in the map.
- First posted on arXiv 20 Feb 2023.

## Builds on (most cited first, 23 of 23)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [Kornia: an Open Source Differentiable Computer Vision Library for PyTorch](https://mlsanity.com/paper/1910.02190/) (2019)
- [Image Matching across Wide Baselines: From Paper to Practice](https://mlsanity.com/paper/2003.01587/) (2020)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [MAGSAC++, a fast, reliable and accurate robust estimator](https://mlsanity.com/paper/1912.05909/) (2019)
- [Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://mlsanity.com/paper/1908.04964/) (2019)
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [Graph-Cut RANSAC](https://mlsanity.com/paper/1706.00984/) (2017)
- [Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses](https://mlsanity.com/paper/1905.04132/) (2019)
- [On the Limits of Pseudo Ground Truth in Visual Camera Re-localisation](https://mlsanity.com/paper/2109.00524/) (2021)
- [Repeatability Is Not Enough: Learning Affine Regions via Discriminability](https://mlsanity.com/paper/1711.06704/) (2017)
- [Progressive Correspondence Pruning by Consensus Learning](https://mlsanity.com/paper/2101.00591/) (2021)
- [MODS: Fast and Robust Method for Two-View Matching](https://mlsanity.com/paper/1503.02619/) (2015)
- [VSAC: Efficient and Accurate Estimator for H and F](https://mlsanity.com/paper/2106.10240/) (2021)
- [Keyframe-based monocular SLAM: design, survey, and future directions](https://mlsanity.com/paper/1607.00470/) (2016)
- [Making Affine Correspondences Work in Camera Geometry Computation](https://mlsanity.com/paper/2007.10032/) (2020)
- [ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning](https://mlsanity.com/paper/1907.02545/) (2019)
- [A Two-point Method for PTZ Camera Calibration in Sports](https://mlsanity.com/paper/1801.09005/) (2018)
- [Effect of Parameter Optimization on Classical and Learning-based Image Matching Methods](https://mlsanity.com/paper/2108.08179/) (2021)

## Built on by (most cited first, 15 of 15)

- [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://mlsanity.com/paper/2304.02008/) (2023)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [SupeRANSAC: One RANSAC to Rule Them All](https://mlsanity.com/paper/2506.04803/) (2025)
- [Image Matching by Bare Homography](https://mlsanity.com/paper/2305.08946/) (2023)
- [Image Matching Filtering and Refinement by Planes and Beyond](https://mlsanity.com/paper/2411.09484/) (2024)
- [RANSAC Scoring Functions: Analysis and Reality Check](https://mlsanity.com/paper/2512.19850/) (2025)
- [SIDAR: Synthetic Image Dataset for Alignment & Restoration](https://mlsanity.com/paper/2305.12036/) (2023)
- [LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching](https://mlsanity.com/paper/2510.16438/) (2025)
- [Fixing the RANSAC Stopping Criterion](https://mlsanity.com/paper/2503.07829/) (2025)
- [RANSAC Scoring Done Right](https://mlsanity.com/paper/2606.27385/) (2026)
- [Good Keypoints for the Two-View Geometry Estimation Problem](https://mlsanity.com/paper/2503.18767/) (2025)
- [Radially Distorted Homographies, Revisited](https://mlsanity.com/paper/2508.21190/) (2025)
- [Robust Multi-Model Fitting through Learning Neighbor Regions](https://mlsanity.com/paper/2609.15348/) (2026)
- [DABACO: A Multi-Camera Dataset and Benchmark for Screen Localization and Pointing Estimation](https://mlsanity.com/paper/2610.03928/) (2026)
- [Robust Local Optimization Done Right](https://mlsanity.com/paper/2610.05743/) (2026)

## Abstract (arXiv)

We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D. The applications of the Pi3D dataset are diverse, e.g. training or evaluating monocular depth, surface normal estimation and image matching algorithms. The HEB dataset consists of 226 260 homographies and includes roughly 4M correspondences. The homographies link images that often undergo significant viewpoint and illumination changes. As applications of HEB, we perform a rigorous evaluation of a wide range of robust estimators and deep learning-based correspondence filtering methods, establishing the current state-of-the-art in robust homography estimation. We also evaluate the uncertainty of the SIFT orientations and scales w.r.t. the ground truth coming from the underlying homographies and provide codes for comparing uncertainty of custom detectors. The dataset is available at urlhttps://github.com/danini/homography-benchmark.