# deep_image_homography_estimation

**Repository Path**: repe/deep_image_homography_estimation

## Basic Information

- **Project Name**: deep_image_homography_estimation
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-10-24
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# deep image homography estimation
This code is writen by jupyter notebook with keras to implement this paper:
DeTone D, Malisiewicz T, Rabinovich A. Deep image homography estimation[J]. arXiv preprint arXiv:1606.03798, 2016.
https://arxiv.org/abs/1606.03798

This model is build on this proiect:  https://github.com/alexhagiopol/deep_homography_estimation

train:
You should put all the jpg images into the test_images directory.
if you want to train the whole model , you can change steps_per_epoch to adjust iterations.

test:
if you don't want to train the whole model ,you can get a pretrained model from here:https://drive.google.com/open?id=0B88aZDadyYr8TTBSY3JvYTVKVnc