Joint Recovery of Dense Correspondence and Cosegmentation in Two Images
Joint Recovery of Dense Correspondence and Cosegmentation in Two Images
复制标题
DOI：
10.1109/cvpr.2016.460
复制
发表时间：
2016-06
期刊：
影响因子：
--
通讯作者：
Tatsunori Taniai;Sudipta N. Sinha;Yoichi Sato
中科院分区：
文献类型：
--
作者：
Tatsunori Taniai;Sudipta N. Sinha;Yoichi Sato
我们提出了一种新的方法来联合恢复两幅图像的共分割和密集的每像素对应关系。我们的方法使用分段相似变换来对对应关系场进行参数化，并恢复两幅图像中估计的共同“前景”区域之间的映射，从而允许它们精确地对齐。我们的公式是基于具有分割和变换标签的分层马尔可夫随机场模型。该分层结构使用嵌套的图像区域来约束跨多个尺度的推理。不同于以往的层次化方法假设结构是给定的，我们提出的迭代技术在标记的同时动态地恢复结构。该联合推理是在使用迭代图切割的能量最小化框架中执行的。我们在包含400幅人工获取的地面真实图像的新数据集上对我们的方法进行了评估，在这些数据集上，我们的方法比专门为协同分割或对应估计设计的最先进的方法要好。
We propose a new technique to jointly recover cosegmentation and dense per-pixel correspondence in two images. Our method parameterizes the correspondence field using piecewise similarity transformations and recovers a mapping between the estimated common "foreground" regions in the two images allowing them to be precisely aligned. Our formulation is based on a hierarchical Markov random field model with segmentation and transformation labels. The hierarchical structure uses nested image regions to constrain inference across multiple scales. Unlike prior hierarchical methods which assume that the structure is given, our proposed iterative technique dynamically recovers the structure along with the labeling. This joint inference is performed in an energy minimization framework using iterated graph cuts. We evaluate our method on a new dataset of 400 image pairs with manually obtained ground truth, where it outperforms state-of-the-art methods designed specifically for either cosegmentation or correspondence estimation.