FlowNet: Learning Optical Flow with Convolutional Networks

04/26/2015
by   Philipp Fischer, et al.
0

Convolutional neural networks (CNNs) have recently been very successful in a variety of computer vision tasks, especially on those linked to recognition. Optical flow estimation has not been among the tasks where CNNs were successful. In this paper we construct appropriate CNNs which are capable of solving the optical flow estimation problem as a supervised learning task. We propose and compare two architectures: a generic architecture and another one including a layer that correlates feature vectors at different image locations. Since existing ground truth data sets are not sufficiently large to train a CNN, we generate a synthetic Flying Chairs dataset. We show that networks trained on this unrealistic data still generalize very well to existing datasets such as Sintel and KITTI, achieving competitive accuracy at frame rates of 5 to 10 fps.

READ FULL TEXT

page 1

page 3

page 6

page 8

page 11

page 12

page 13

research
10/04/2017

Secrets in Computing Optical Flow by Convolutional Networks

Convolutional neural networks (CNNs) have been widely used over many are...
research
11/08/2020

FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition

Capsule networks (CapsNets) have recently shown promise to excel in most...
research
04/24/2018

Cubes3D: Neural Network based Optical Flow in Omnidirectional Image Scenes

Optical flow estimation with convolutional neural networks (CNNs) has re...
research
12/12/2016

Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild

CNN-based optical flow estimation has attracted attention recently, main...
research
04/06/2020

Optical Flow Estimation in the Deep Learning Age

Akin to many subareas of computer vision, the recent advances in deep le...
research
03/11/2019

Demonstration of Vector Flow Imaging using Convolutional Neural Networks

Synthetic Aperture Vector Flow Imaging (SA-VFI) can visualize complex ca...
research
09/02/2020

When Deep Learning Meets Digital Image Correlation

Convolutional Neural Networks (CNNs) constitute a class of Deep Learning...

Please sign up or login with your details

Forgot password? Click here to reset