图 书 馆
PMBP：用于对应场估计的匹配信念传播算法PMBP: PatchMatch Belief Propagation for Correspondence Field Estimation |
|
| 课程网址: | http://videolectures.net/bmvc2012_besse_belief_propagation/ |
| 主讲教师: | Frederic Besse |
| 开课单位: | 伦敦大学 |
| 开课时间: | 2012-10-09 |
| 课程语种: | 英语 |
| 中文简介: |  PatchMatch是用于优化连续标签问题的简单但功能强大且成功的方法。该算法具有两个主要成分：通过采样更新解空间以及使用空间邻域传播采样。我们展示了这些成分如何与在连续空间中以特定形式的信念传播（称为粒子信念传播（PBP））的步骤相关。但是，到目前为止，PBP太慢了，无法允许复杂的状态空间。我们表明，将这两种方法结合起来会产生一种新算法PMBP，它比PatchMatch更准确，并且比PBP快几个数量级。为了说明我们的PMBP方法的好处，我们建立了一个新的立体声匹配算法，该算法使用了一元项，这些项是从最近的PatchMatch立体声工作中借用的，以及新颖的，成对的，提供平滑性的项。我们已经通过实验验证了我们的方法是对亚像素精度级别的最新技术的改进。 |
| 课程简介: | PatchMatch is a simple, yet very powerful and successful method for optimizing continuous labelling problems. The algorithm has two main ingredients: the update of the solution space by sampling and the use of the spatial neighbourhood to propagate samples. We show how these ingredients are related to steps in a specific form of belief propagation in the continuous space, called Particle Belief Propagation (PBP). However, PBP has thus far been too slow to allow complex state spaces. We show that unifying the two approaches yields a new algorithm, PMBP, which is more accurate than PatchMatch and orders of magnitude faster than PBP. To illustrate the benefits of our PMBP method we have built a new stereo matching algorithm with unary terms which are borrowed from the recent PatchMatch Stereo work and novel realistic pairwise terms that provide smoothness. We have experimentally verified that our method is an improvement over state-of-the-art techniques at sub-pixel accuracy level. |
| 关 键 词: | 算法结合; 新算法 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-03-25：zyk |
| 最后编审: | 2021-03-25：zyk |
| 阅读次数: | 51 |