Abstract
We present a compact but effective CNN model for optical flow, called PWC-Net. PWC-Net has been designed according to simple and well-established principles: pyramidal processing, warping, and the use of a cost volume. Cast in a learnable feature pyramid, PWC-Net uses the cur- rent optical flow estimate to warp the CNN features of the second image. It then uses the warped features and features of the first image to construct a cost volume, which is processed by a CNN to estimate the optical flow. PWC-Net is 17 times smaller in size and easier to train than the recent FlowNet2 model. Moreover, it outperforms all published optical flow methods on the MPI Sintel final pass and KITTI 2015 benchmarks, running at about 35 fps on Sintel resolution (1024x436) images. Our models are available on https://github.com/NVlabs/PWC-Net.
Abstract (translated)
我们提出了一种紧凑但有效的光纤流量CNN模型,称为PWC-Net。 PWC-Net的设计遵循了简单明了的原则:锥体加工,翘曲和成本卷的使用。在可学习的特征金字塔中,PWC-Net使用当前的光流估计扭曲第二幅图像的CNN特征。然后它使用第一幅图像的变形特征和特征来构造成本体积,由CNN处理该成本体积以估计光流。与最近的FlowNet2型号相比,PWC-Net的尺寸缩小了17倍,并且更容易培训。此外,它在Sintel分辨率(1024x436)图像上的运行速度大约为35 fps,优于MPI Sintel最终通过版和KITTI 2015基准测试版上发布的所有光学流方法。我们的模型可在https://github.com/NVlabs/PWC-Net上找到。
URL
https://arxiv.org/abs/1709.02371