Abstract
Deep learning approaches to optical flow estimation have seen rapid progress over the recent years. One common trait of many networks is that they refine an initial flow estimate either through multiple stages or across the levels of a coarse-to-fine representation. While leading to more accurate results, the downside of this is an increased number of parameters. Taking inspiration from both classical energy minimization approaches as well as residual networks, we propose an iterative residual refinement (IRR) scheme based on weight sharing that can be combined with several backbone networks. It reduces the number of parameters, improves the accuracy, or even achieves both. Moreover, we show that integrating occlusion prediction and bi-directional flow estimation into our IRR scheme can further boost the accuracy. Our full network achieves state-of-the-art results for both optical flow and occlusion estimation across several standard datasets.
Abstract (translated)
近几年来,光流量估计的深度学习方法取得了迅速的进展。许多网络的一个共同特点是,它们可以通过多个阶段或从粗到细的表示级别来优化初始流估计。虽然这会导致更准确的结果,但缺点是参数数量增加。本文从经典的能量最小化方法和剩余网络两个方面出发,提出了一种基于权值分担的迭代剩余细化(IRR)方案,该方案可以与多个主干网络相结合。它减少了参数的数量,提高了精度,甚至实现了这两者。此外,我们还表明,将遮挡预测和双向流估计结合到IRR方案中可以进一步提高精度。我们的全网络可在多个标准数据集中实现最先进的光流量和遮挡估计结果。
URL
https://arxiv.org/abs/1904.05290