论文标题
Starflow：轻质多帧光流估计的时空复发单元
STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation
论文作者
论文摘要
我们提出了一种新的基于CNN的重量级基于CNN的算法，用于多帧光流估计。我们的解决方案通过重复使用通用的“星”（时空复发）细胞引入了双重复发和时间的双重复发。它包括（i）基于传达学习特征而不是光流估计的时间复发； （ii）一个遮挡检测过程，与光流估计相结合，因此使用了非常有限的额外参数。所得的Starflow算法可在MPI Sintel和Kitti2015上提供最先进的性能，并且与所有其他方法相比，参数的参数少得多。
We present a new lightweight CNN-based algorithm for multi-frame optical flow estimation. Our solution introduces a double recurrence over spatial scale and time through repeated use of a generic "STaR" (SpatioTemporal Recurrent) cell. It includes (i) a temporal recurrence based on conveying learned features rather than optical flow estimates; (ii) an occlusion detection process which is coupled with optical flow estimation and therefore uses a very limited number of extra parameters. The resulting STaRFlow algorithm gives state-of-the-art performances on MPI Sintel and Kitti2015 and involves significantly less parameters than all other methods with comparable results.
