Deep Image Homography Estimation

Code

• github.com/mazenmel/Deep-homography-estimation-Pytorch
  pytorch★ 152
• github.com/DangChuong-DC/Toy-Homography
  tf★ 0
• github.com/samorr/homography-net
  none★ 0
• github.com/JirongZhang/DeepHomography
  pytorch★ 0
• github.com/richard-guinto/homographynet
  tf★ 0
• github.com/mez/deep_homography_estimation
  none★ 0
• github.com/fjbriones/deep-homography
  none★ 0
• github.com/Phirxian/phd-airphen-alignment
  none★ 0

Abstract

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.

Tasks

Reproductions