Sorry, you need to enable JavaScript to visit this website.


DenseNet for Dense Flow


Classical approaches for estimating optical flow have achieved rapid progress in the last decade. However, most of them are too slow to be applied in real-time video analysis. Due to the great success of deep learning, recent work has focused on using CNNs to solve such dense prediction problems. In this paper, we investigate a new deep architecture, Densely Connected Convolutional Networks (DenseNet), to learn optical flow. This specific architecture is ideal for the problem at hand as it provides shortcut connections throughout the network, which leads to implicit deep supervision. We extend current DenseNet to a fully convolutional network to learn motion estimation in an unsupervised manner. Evaluation results on three standard benchmarks demonstrate that DenseNet is a better fit than other widely adopted CNN architectures for optical flow estimation.

0 users have voted:

Paper Details

Yi Zhu,Shawn Newsam
Submitted On:
16 September 2017 - 2:45am
Short Link:
Presentation Slides
Presenter's Name:
Yi Zhu
Paper Code:
Document Year:

Document Files




[1] Yi Zhu,Shawn Newsam, "DenseNet for Dense Flow", IEEE SigPort, 2017. [Online]. Available: Accessed: Jul. 23, 2019.
url = {},
author = {Yi Zhu;Shawn Newsam },
publisher = {IEEE SigPort},
title = {DenseNet for Dense Flow},
year = {2017} }
T1 - DenseNet for Dense Flow
AU - Yi Zhu;Shawn Newsam
PY - 2017
PB - IEEE SigPort
UR -
ER -
Yi Zhu,Shawn Newsam. (2017). DenseNet for Dense Flow. IEEE SigPort.
Yi Zhu,Shawn Newsam, 2017. DenseNet for Dense Flow. Available at:
Yi Zhu,Shawn Newsam. (2017). "DenseNet for Dense Flow." Web.
1. Yi Zhu,Shawn Newsam. DenseNet for Dense Flow [Internet]. IEEE SigPort; 2017. Available from :