图 书 馆
一种全局最优数据驱动的图像失真估计方法A Globally Optimal Data-Driven Approach for Image Distortion Estimation |
|
| 课程网址: | http://videolectures.net/cvpr2010_tian_godd/ |
| 主讲教师: | Yuandong Tian |
| 开课单位: | 卡内基梅隆大学 |
| 开课时间: | 2010-09-19 |
| 课程语种: | 英语 |
| 中文简介: |  在存在非刚性变形的情况下进行图像对齐是一项艰巨的任务。通常，这涉及估计密集变形场的参数，该变形场将扭曲的图像扭曲回到其未扭曲的模板。基于参数优化的生成方法（例如Lucas Kanade）可能会陷入局部极小值之内。另一方面，诸如最近邻居之类的判别方法需要大量训练样本，并且训练样本以所需的精度呈指数增长。在这项工作中，我们开发了一种新颖的数据驱动的迭代算法，该算法结合了生成方法和判别方法的优点。为此，我们引入了“拉回”操作的概念，该操作使我们能够使用不在参数空间中其附近（不是ε接近）的训练样本来预测测试图像的参数。我们证明了我们的算法使用数量很少的训练样本收敛到全局最优，训练样本仅以对数增长且具有所需的精度。我们使用综合数据对算法的行为进行了广泛分析，并在因水和衣服引起的复杂变形的实验中证明了成功的结果。 |
| 课程简介: | Image alignment in the presence of non-rigid distortions is a challenging task. Typically, this involves estimating the parameters of a dense deformation field that warps a distorted image back to its undistorted template. Generative approaches based on parameter optimization such as Lucas-Kanade can get trapped within local minima. On the other hand, discriminative approaches like Nearest-Neighbor require a large number of training samples that grows exponentially with the desired accuracy. In this work, we develop a novel data-driven iterative algorithm that combines the best of both generative and discriminative approaches. For this, we introduce the notion of a “pull-back” operation that enables us to predict the parameters of the test image using training samples that are not in its neighborhood (not ε-close) in parameter space. We prove that our algorithm converges to the global optimum using a significantly lower number of training samples that grows only logarithmically with the desired accuracy. We analyze the behavior of our algorithm extensively using synthetic data and demonstrate successful results on experiments with complex deformations due to water and clothing. |
| 关 键 词: | 图像测试; 参数空间; 算法迭代 |
| 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: | 37 |