|
一个全局最优的图像失真估计的数据驱动的方法
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: |
2010-07-19
|
| 课程语种: |
英语
|
| 中文简介: |
在存在非刚性扭曲的情况下进行图像对准是一项具有挑战性的任务。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其未失真的模板。基于参数优化的基因方法（例如Lucas Kanade）可能陷入局部最小值。另一方面，像最近邻的判别方法需要大量的培训样本以预期的准确度呈指数增长。在这项工作中，我们开发了一种新颖的数据驱动迭代算法，它结合了生成和判别方法的优点。为此，我们引入了“回拉”操作的概念，使我们能够使用参数空间中不在其邻域（非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收敛于全局最优使用训练样本数量明显减少，只能以所需精度对数增长。我们使用合成数据广泛分析了算法的行为，并证明了由于水和衣物引起的复杂变形实验的成功结果。
|
| 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: |
非刚性扭曲; 图像对准; 数据驱动
|
| 课程来源: |
视频讲座网
|
| 最后编审: |
2020-06-22：chenxin
|
| 阅读次数: |
30
|
|
图 书 馆