论文标题
多尺度筏：结合基于学习的光流估计的分层概念
Multi-Scale RAFT: Combining Hierarchical Concepts for Learning-based Optical FLow Estimation
论文作者
论文摘要
许多基于经典和学习的光流方法依赖于分层概念来提高准确性和鲁棒性。但是，目前最成功的方法之一 - 筏 - 几乎无法利用这种概念。在这项工作中，我们表明多尺度的想法仍然很有价值。更确切地说，使用筏作为基线，我们提出了一个新型的多尺度神经网络，将几个分层概念结合在单个估计框架中。这些概念包括（i）部分共享的粗到精细结构，（ii）多尺度功能，（iii）层次成本量和（iv）多尺度的多材料损失。 MPI Sintel和Kitti的实验清楚地证明了我们方法的好处。与筏相比，它们不仅显示出实质性的改善，而且还显示出最先进的结果，尤其是在非封闭区域中。代码将在https://github.com/cv-stuttgart/ms_raft上找到。
Many classical and learning-based optical flow methods rely on hierarchical concepts to improve both accuracy and robustness. However, one of the currently most successful approaches -- RAFT -- hardly exploits such concepts. In this work, we show that multi-scale ideas are still valuable. More precisely, using RAFT as a baseline, we propose a novel multi-scale neural network that combines several hierarchical concepts within a single estimation framework. These concepts include (i) a partially shared coarse-to-fine architecture, (ii) multi-scale features, (iii) a hierarchical cost volume and (iv) a multi-scale multi-iteration loss. Experiments on MPI Sintel and KITTI clearly demonstrate the benefits of our approach. They show not only substantial improvements compared to RAFT, but also state-of-the-art results -- in particular in non-occluded regions. Code will be available at https://github.com/cv-stuttgart/MS_RAFT.
