一种用于超图匹配的弹性张量块坐标上升方案
A Flexible Tensor Block Coordinate Ascent Scheme for Hypergraph Matching
摘要：
两幅图像之间对应关系的估计。点集是计算机视觉的核心问题。一种方法来制定的问题是图匹配导致的二次分配问题，这是NP-难。已经提出了几个所谓的二阶方法来解决这个问题。近年来，超图匹配导致的三阶问题变得流行，因为它允许更好地整合几何信息。对于大多数这些三阶算法没有理论保证是已知的。在本文中，我们提出了一个总体框架张量块坐标上升方法超图匹配。我们提出了两个算法，这两个算法都来与离散分配矩阵的集合上的匹配分数的单调上升的保证。在实验中，我们表明，我们的新算法优于以前的工作，无论是在实现更好的匹配分数和匹配精度。这尤其适用于非常具有挑战性的设置，其中具有大量的离群值和其他形式的噪声。
英文摘要：
The estimation of correspondences between two images resp. point sets is a core problem in computer vision. One way to formulate the problem is graph matching leading to the quadratic assignment problem which is NP-hard. Several so called second order methods have been proposed to solve this problem. In recent years hypergraph matching leading to a third order problem became popular as it allows for better integration of geometric information. For most of these third order algorithms no theoretical guarantees are known. In this paper we propose a general framework for tensor block coordinate ascent methods for hypergraph matching. We propose two algorithms which both come along with the guarantee of monotonic ascent in the matching score on the set of discrete assignment matrices. In the experiments we show that our new algorithms outperform previous work both in terms of achieving better matching scores and matching accuracy. This holds in particular for very challenging settings where one has a high number of outliers and other forms of noise.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
