Published on Sun Apr 05 2020

Deep Homography Estimation for Dynamic Scenes

Hoang Le, Feng Liu, Shu Zhang, Aseem Agarwala

Homography estimation is an important step in many computer vision problems. This paper investigates and discusses how to design and train a deep neural network that handles dynamic scenes.

0
0
0
Abstract

Homography estimation is an important step in many computer vision problems. Recently, deep neural network methods have shown to be favorable for this problem when compared to traditional methods. However, these new methods do not consider dynamic content in input images. They train neural networks with only image pairs that can be perfectly aligned using homographies. This paper investigates and discusses how to design and train a deep neural network that handles dynamic scenes. We first collect a large video dataset with dynamic content. We then develop a multi-scale neural network and show that when properly trained using our new dataset, this neural network can already handle dynamic scenes to some extent. To estimate a homography of a dynamic scene in a more principled way, we need to identify the dynamic content. Since dynamic content detection and homography estimation are two tightly coupled tasks, we follow the multi-task learning principles and augment our multi-scale network such that it jointly estimates the dynamics masks and homographies. Our experiments show that our method can robustly estimate homography for challenging scenarios with dynamic scenes, blur artifacts, or lack of textures.

Mon Jun 13 2016
Computer Vision
Deep Image Homography Estimation
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.
0
0
0
Tue Jul 06 2021
Computer Vision
Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation
Homography estimation is an important task in computer vision. Traditional homography estimation methods heavily depend on quantity and distribution of feature points. We propose to predict multi-grid homography from global to local. We equip our network with depth perception capability.
1
0
1
Thu Sep 12 2019
Computer Vision
Flow-Motion and Depth Network for Monocular Stereo and Beyond
We propose a learning-based method that solves monocular stereo and can be extended to fuse depth information from multiple target frames. Given two images from a monocular camera with known intrinsic calibration, our network estimates relative camera poses and the depth map of the source image.
0
0
0
Mon Oct 08 2018
Computer Vision
Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos
The paper was written by Baidu researchers. It uses deep neural networks to learn depth and optical flow from videos.
0
0
0
Tue Sep 12 2017
Computer Vision
Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model
Homography estimation on a robotic system requires a fast and robust homography estimation algorithm. We propose an unsupervised learning algorithm that trains a Deep Convolutional Neural Network to estimate planar homographies.
0
0
0
Fri Oct 02 2020
Computer Vision
Homography Estimation with Convolutional Neural Networks Under Conditions of Variance
Planar homography estimation is foundational to many computer vision problems. However, conditions of high variance confound even the state-of-the-art algorithms. In this report, we analyze the performance of two recently published methods using Convolutional Neural Networks.
0
0
0