Modern large displacement optical flow algorithms usually use an initialization by either sparse descriptor matching techniques or dense approximate nearest neighbor fields. While the latter have the advantage of being dense, they have the major disadvantage of being very outlier-prone as they are not designed to find the optical flow, but the visually most similar correspondence. In this article we present a dense correspondence field approach that is much less outlier-prone and thus much better suited for optical flow estimation than approximate nearest neighbor fields. Our approach does not require explicit regularization, smoothing (like median filtering) or a new data term. Instead we solely rely on patch matching techniques and a novel multi-scale matching strategy. We also present enhancements for outlier filtering. We show that our approach is better suited for large displacement optical flow estimation than modern descriptor matching techniques. We do so by initializing EpicFlow with our approach instead of their originally used state-of-the-art descriptor matching technique. We significantly outperform the original EpicFlow on MPI-Sintel, KITTI 2012, KITTI 2015 and Middlebury. In this extended article of our former conference publication we further improve our approach in matching accuracy as well as runtime and present more experiments and insights.

中文翻译：

---

流场：用于高精确度大位移光流估计的密集对应场

现代大位移光流算法通常使用稀疏描述符匹配技术或密集的近似最近邻场进行初始化。尽管后者具有致密的优点，但是它们的主要缺点是非常容易发生离群值，因为它们不是为了找到光流而是在视觉上最相似的对应关系而设计的。在本文中，我们提出了一种密集的对应场方法，该方法比异常最近的邻域更不容易出现离群值，因此更适合于光流估计。我们的方法不需要显式的正则化，平滑（如中值滤波）或新的数据项。相反，我们仅依靠补丁匹配技术和新颖的多尺度匹配策略。我们还提出了针对异常值过滤的增强功能。我们表明，与现代描述符匹配技术相比，我们的方法更适合于大位移光流估计。我们通过使用我们的方法而不是最初使用的最新描述符匹配技术来初始化EpicFlow来实现。在MPI-Sintel，KITTI 2012，KITTI 2015和Middlebury上，我们的性能明显优于原始EpicFlow。在我们以前的会议出版物的这篇扩展文章中，我们进一步改进了匹配精度和运行时的方法，并提供了更多的实验和见解。KITTI 2012，KITTI 2015和Middlebury。在我们以前的会议出版物的这篇扩展文章中，我们进一步改进了匹配精度和运行时的方法，并提供了更多的实验和见解。KITTI 2012，KITTI 2015和Middlebury。在我们以前的会议出版物的这篇扩展文章中，我们进一步改进了匹配精度和运行时的方法，并提供了更多的实验和见解。