图像拼接--Coarse-to-fine Seam Estimation for Image Stitching

Coarse-to-fine Seam Estimation for Image Stitching https://arxiv.org/abs/1805.09578

本文主要针对图像拼接中的缝合线选择的改进。 以前的缝合线选择主要 measure the average performance of the pixels on the seam without considering the relevance and variance among them。 这么做可能造成的问题是 最优的 缝合线 在 人眼视觉上不是最好的 （perception-inconsistent）。 这里我们设计了一个新的 patch-point evaluation algorithm 用于 缝合线的迭代确定。最终得到的缝合线是 nearly perception-consistent seam

coarse-to-fine seam estimation framework A. Conventional Seam-cutting 传统的缝合线确定主要是通过定义能量函数， 通过 minimized via graph cuts 得到 缝合线 能量函数定义如下：

在这里插入图片描述

上述函数的优化通过下面的算法求解。 Fast approximate energy minimization via graph cuts

B. Patch-point Evaluation Algorithm 文献【12,13】定义了一个 ZNCC-based method 来评估 the stitching seam

在这里插入图片描述

如上图所示，这样的缝合线可能不是 human perception 最佳的 such quality measures the average performance of these pixels without considering the relevance and variance among them. It may cause that the seam with the minimal measure is not optimal in human perception

这里我们改进了一下 Seam estimation ，结合 patch 和 point the patch differences have a good “continuity” property while the point differences have a nice “diversity” property (see Fig. 2). Thus, we combine the patch and point together to evaluate the seam.

在这里插入图片描述

1. Patch evaluation: 这里我们采用 SSIM (structural similarity) index 来 compare the local patches in the two images. 没有采用 ZNCC a misaligned pixel on the seam usually possesses a relatively large value of patch evaluation
2. Point evaluation: The point evaluation measures the color difference between the pixels on the two sides of the seam. Thus, a plausible seam would have a relatively small value of point evaluation for (nearly) all pixels on the seam. This can avoid the false positives in the patch evaluation

在这里插入图片描述

速度应该不会太快！