Learning Optical Flow Using Deep Dilated Residual Networks

Learning Optical Flow Using Deep Dilated Residual Networks

Nowadays, convolutional neural networks achieve remarkable performance on optical flow estimation because of its strong non-linear fitting ability. Most of them adopt the U-Net architecture, which contains an encoder part and a decoder part. In the encoder part, the resolution of the feature map is...

Full description

Bibliographic Details
Main Authors: Mingliang Zhai, Xuezhi Xiang, Rongfang Zhang, Ning Lv, Abdulmotaleb El Saddik
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Optical flow estimation
convolutional neural networks
residual network
dilated convolution
prior multi-constraint loss
Online Access:https://ieeexplore.ieee.org/document/8640114/

Internet

https://ieeexplore.ieee.org/document/8640114/

Similar Items