当前位置: X-MOL 学术Int. J. Comput. Vis. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Learning Multi-human Optical Flow
International Journal of Computer Vision ( IF 19.5 ) Pub Date : 2020-01-02 , DOI: 10.1007/s11263-019-01279-w
Anurag Ranjan , David T. Hoffmann , Dimitrios Tzionas , Siyu Tang , Javier Romero , Michael J. Black

The optical flow of humans is well known to be useful for the analysis of human action. Recent optical flow methods focus on training deep networks to approach the problem. However, the training data used by them does not cover the domain of human motion. Therefore, we develop a dataset of multi-human optical flow and train optical flow networks on this dataset. We use a 3D model of the human body and motion capture data to synthesize realistic flow fields in both single- and multi-person images. We then train optical flow networks to estimate human flow fields from pairs of images. We demonstrate that our trained networks are more accurate than a wide range of top methods on held-out test data and that they can generalize well to real image sequences. The code, trained models and the dataset are available for research.

中文翻译:

学习多人光流

众所周知,人类的光流可用于分析人类行为。最近的光流方法侧重于训练深度网络来解决这个问题。然而,他们使用的训练数据并没有涵盖人体运动的领域。因此,我们开发了一个多人光流数据集并在该数据集上训练光流网络。我们使用人体的 3D 模型和运动捕捉数据来合成单人和多人图像中的真实流场。然后我们训练光流网络从成对的图像中估计人流场。我们证明,我们训练的网络在保留的测试数据上比各种顶级方法更准确,并且它们可以很好地推广到真实图像序列。代码、经过训练的模型和数据集可供研究使用。
更新日期:2020-01-02
down
wechat
bug