论文标题
FDFLOWNET：使用深度轻量级网络的快速光流估算
FDFlowNet: Fast Optical Flow Estimation using a Deep Lightweight Network
论文作者
论文摘要
使用深神经网络估算光流，已经取得了重大进展。高级深层模型通常通过相当大的计算复杂性和耗时的训练过程来实现准确的流量估计。在这项工作中，我们提出了一个轻巧但有效的模型，用于实时光流估计，称为FDFLOWNET（快速深部飞行员）。我们在具有挑战性的Kitti和Sintel基准测试中获得更好或类似的精度，而比PWC-NET快2倍。这是通过精心设计的结构和新提出的组件来实现的。我们首先引入了一个U形网络，用于构建多尺度功能，该功能与金字塔网络相比，它具有全球接受场的上层级别。在每个尺度中，提出了一个具有扩张卷积的部分完全连接的结构，以进行流量估计，该结构与连接和密集连接的结构相比，速度，准确性和参数数量之间达到了良好的平衡。实验表明，我们的模型在快速和轻巧的同时达到了最先进的性能。
Significant progress has been made for estimating optical flow using deep neural networks. Advanced deep models achieve accurate flow estimation often with a considerable computation complexity and time-consuming training processes. In this work, we present a lightweight yet effective model for real-time optical flow estimation, termed FDFlowNet (fast deep flownet). We achieve better or similar accuracy on the challenging KITTI and Sintel benchmarks while being about 2 times faster than PWC-Net. This is achieved by a carefully-designed structure and newly proposed components. We first introduce an U-shape network for constructing multi-scale feature which benefits upper levels with global receptive field compared with pyramid network. In each scale, a partial fully connected structure with dilated convolution is proposed for flow estimation that obtains a good balance among speed, accuracy and number of parameters compared with sequential connected and dense connected structures. Experiments demonstrate that our model achieves state-of-the-art performance while being fast and lightweight.
