https://github.com/alexhagiopol/deep_homography_estimation

Compute homographies with deep networks instead of feature matching and RANSAC.

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.

首先制作大量的训练图像，通过四点仿射模型，然后用深度学习训练，取得了比ORB要好的结果。

可是，为什么不跟sift比呢。。。。