DenseNet for Dense Flow

TL;DR

This paper introduces a DenseNet-based deep learning architecture for optical flow estimation, demonstrating improved accuracy and efficiency over existing CNN methods through unsupervised learning on standard benchmarks.

Contribution

The paper extends DenseNet to a fully convolutional, unsupervised model specifically designed for optical flow estimation, showing its superiority over other CNN architectures.

Findings

DenseNet outperforms other CNNs in optical flow accuracy.

The proposed model operates efficiently for real-time applications.

Unsupervised training achieves competitive results on benchmarks.

Abstract

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.