Fast Cost-Volume Filtering for Visual Correspondence and Beyond
Fast Cost-Volume Filtering for Visual Correspondence and Beyond
复制标题
DOI：
10.1109/tpami.2012.156
复制
发表时间：
2013-02-01
影响因子：
23.6
通讯作者：
Gelautz, Margrit
中科院分区：
文献类型：
--
作者：
Hosni, Asmaa;Rhemann, Christoph;Gelautz, Margrit
许多计算机视觉任务可以被公式化为标记问题。所需的解决方案通常是空间平滑的标记，其中标签过渡与输入图像的颜色边缘对齐。我们表明，这样的解决方案可以有效地实现平滑的标签成本与一个非常快速的边缘保持过滤器。在本文中，我们提出了一个通用和简单的框架，包括三个步骤：1）构建成本卷，2）快速成本卷过滤，3）赢家通吃标签选择。我们的主要贡献是表明，有了这样一个简单的框架，国家的最先进的结果可以实现几个计算机视觉应用。特别是，我们实现了1）视差图在真实的时间，其质量超过了所有其他快速（本地）的方法在米德尔伯里立体基准，和2）光流场，其中包含非常精细的结构，以及大位移。为了证明鲁棒性，我们的框架的几个参数被设置为几乎相同的值为两个应用程序。此外，交互式图像分割的竞争结果。通过这项工作，我们希望激励其他研究人员利用这个框架到其他应用领域。
Many computer vision tasks can be formulated as labeling problems. The desired solution is often a spatially smooth labeling where label transitions are aligned with color edges of the input image. We show that such solutions can be efficiently achieved by smoothing the label costs with a very fast edge-preserving filter. In this paper, we propose a generic and simple framework comprising three steps: 1) constructing a cost volume, 2) fast cost volume filtering, and 3) Winner-Takes-All label selection. Our main contribution is to show that with such a simple framework state-of-the-art results can be achieved for several computer vision applications. In particular, we achieve 1) disparity maps in real time whose quality exceeds those of all other fast (local) approaches on the Middlebury stereo benchmark, and 2) optical flow fields which contain very fine structures as well as large displacements. To demonstrate robustness, the few parameters of our framework are set to nearly identical values for both applications. Also, competitive results for interactive image segmentation are presented. With this work, we hope to inspire other researchers to leverage this framework to other application areas.