# Deep Image Homography Estimation

arXiv: https://arxiv.org/abs/1606.03798 · HTML: https://mlsanity.com/paper/1606.03798/

## Key facts

- Cited by 136 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2016.

## Built on by (most cited first, 30 of 136)

- [Theseus: A Library for Differentiable Nonlinear Optimization](https://mlsanity.com/paper/2207.09442/) (2022)
- [Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2211.11505/) (2022)
- [Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator](https://mlsanity.com/paper/2308.16906/) (2023)
- [NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations](https://mlsanity.com/paper/2306.09109/) (2023)
- [Wide-Baseline Relative Camera Pose Estimation with Directional Learning](https://mlsanity.com/paper/2106.03336/) (2021)
- [Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images](https://mlsanity.com/paper/2106.12859/) (2021)
- [TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations](https://mlsanity.com/paper/2103.15982/) (2021)
- [Iterative Deep Homography Estimation](https://mlsanity.com/paper/2203.15982/) (2022)
- [Deep Lucas-Kanade Homography for Multimodal Image Alignment](https://mlsanity.com/paper/2104.11693/) (2021)
- [Viewpoint Invariant Dense Matching for Visual Geolocalization](https://mlsanity.com/paper/2109.09827/) (2021)
- [ObjectStitch: Generative Object Compositing](https://mlsanity.com/paper/2212.00932/) (2022)
- [Input-level Inductive Biases for 3D Reconstruction](https://mlsanity.com/paper/2112.03243/) (2021)
- [Deep Matching Prior: Test-Time Optimization for Dense Correspondence](https://mlsanity.com/paper/2106.03090/) (2021)
- [Parallax-Tolerant Unsupervised Deep Image Stitching](https://mlsanity.com/paper/2302.08207/) (2023)
- [Fully neuromorphic vision and control for autonomous drone flight](https://mlsanity.com/paper/2303.08778/) (2023)
- [Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection](https://mlsanity.com/paper/2103.15346/) (2021)
- [LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation](https://mlsanity.com/paper/2106.04067/) (2021)
- [Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation](https://mlsanity.com/paper/2107.02524/) (2021)
- [Deep Learning for Camera Calibration and Beyond: A Survey](https://mlsanity.com/paper/2303.10559/) (2023)
- [Multi-Spectral Multi-Image Super-Resolution of Sentinel-2 with Radiometric Consistency Losses and Its Effect on Building Delineation](https://mlsanity.com/paper/2111.03231/) (2021)
- [Unsupervised Homography Estimation with Coplanarity-Aware GAN](https://mlsanity.com/paper/2205.03821/) (2022)
- [DFM: A Performance Baseline for Deep Feature Matching](https://mlsanity.com/paper/2106.07791/) (2021)
- [Overcoming Obstructions via Bandwidth-Limited Multi-Agent Spatial Handshaking](https://mlsanity.com/paper/2107.00771/) (2021)
- [Perceptual Loss for Robust Unsupervised Homography Estimation](https://mlsanity.com/paper/2104.10011/) (2021)
- [STRIVE: Scene Text Replacement In Videos](https://mlsanity.com/paper/2109.02762/) (2021)
- [Training-free Geometric Image Editing on Diffusion Models](https://mlsanity.com/paper/2507.23300/) (2025)
- [Uncertainty-aware Unsupervised Multi-Object Tracking](https://mlsanity.com/paper/2307.15409/) (2023)
- [Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation](https://mlsanity.com/paper/2209.05968/) (2022)
- [Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint](https://mlsanity.com/paper/2212.02763/) (2022)
- [GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning](https://mlsanity.com/paper/2301.10018/) (2023)

## Abstract (arXiv)

We present a deep convolutional neural network for estimating the relative homography between a pair of images. Our feed-forward network has 10 layers, takes two stacked grayscale images as input, and produces an 8 degree of freedom homography which can be used to map the pixels from the first image to the second. We present two convolutional neural network architectures for HomographyNet: a regression network which directly estimates the real-valued homography parameters, and a classification network which produces a distribution over quantized homographies. We use a 4-point homography parameterization which maps the four corners from one image into the second image. Our networks are trained in an end-to-end fashion using warped MS-COCO images. Our approach works without the need for separate local feature detection and transformation estimation stages. Our deep models are compared to a traditional homography estimator based on ORB features and we highlight the scenarios where HomographyNet outperforms the traditional technique. We also describe a variety of applications powered by deep homography estimation, thus showcasing the flexibility of a deep learning approach.