Joint Coarse-And-Fine Reasoning for Deep Optical Flow
This work addresses optical flow estimation, a key challenge in computer vision, with an incremental improvement in method efficiency and accuracy.
The paper tackles the problem of optical flow estimation by proposing a joint coarse-and-fine reasoning representation that boosts accuracy and reduces training time, achieving competitive results against state-of-the-art CNN-based solutions on large datasets.
We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning. The coarse reasoning is performed over a discrete classification space to obtain a general rough solution, while the fine details of the solution are obtained over a continuous regression space. In our approach both components are jointly estimated, which proved to be beneficial for improving estimation accuracy. Additionally, we propose a new network architecture, which combines coarse and fine components by treating the fine estimation as a refinement built on top of the coarse solution, and therefore adding details to the general prediction. We apply our approach to the challenging problem of optical flow estimation and empirically validate it against state-of-the-art CNN-based solutions trained from scratch and tested on large optical flow datasets.