论文《FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks》，提出了光流的端到端学习的概念。 质量和速度的巨大提高是由三个主要贡献造成的：
1.我们专注于训练数据，并表明训练期间呈现数据的调度非常重要。
2.我们开发了一种堆叠架构，其包括具有中间光流的第二图像的翘曲。
3.我们通过引入一个专门针对小运动的子网络。
摘要：
The FlowNet demonstrated that optical flow estimation can be cast as a learning problem. However, the state of the art with regard to the quality of the flow has still been defined by traditional methods. Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods. In this paper, we advance the concept of end-to-end learning of optical flow and make it work really well. The large improvements in quality and speed are caused by three major contributions: first, we focus on the training data and show that the schedule of presenting data during training is very important. Second, we develop a stacked architecture that includes warping of the second image with intermediate optical flow. Third, we elaborate on small displacements by introducing a sub-network specializing on small motions. FlowNet 2.0 is only marginally slower than the original FlowNet but decreases the estimation error by more than 50%. It performs on par with state-of-the-art methods, while running at interactive frame rates. Moreover, we present faster variants that allow optical flow computation at up to 140fps with accuracy matching the original FlowNet.
链接：
http://lmb.informatik.uni-freiburg.de/Publications/2016/IMKDB16/
原文链接：
http://weibo.com/5501429448/Eu6KR0X8F?ref=collection&type=comment
