资源分类
》 资源 》论文》Optical Flow Requires Multiple Strategies (but only one network)

Optical Flow Requires Multiple Strategies (but only one network)

2019-12-04 | |  47 |   47 |   0

Abstract

We show that the matching problem that underlies optical flflow requires multiple strategies, depending on the amount of image motion and other factors. We then study the implications of this observation on training a deep neural network for representing image patches in the context of descriptor based optical flflow. We propose a metric learning method, which selects suitable negative samples based on the nature of the true match. This type of training produces a network that displays multiple strategies depending on the input and leads to state of the art results on the KITTI 2012 and KITTI 2015 optical flflow benchmarks.

上一篇：Optical Flow in Mostly Rigid Scenes

下一篇：Order-preserving Wasserstein Distance for Sequence Matching

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...