|
低层视觉中磁共振的生成视角
A Generative Perspective on MRFs in Low-Level Vision |
|
| |
| 课程网址: |
http://videolectures.net/cvpr2010_schmidt_gpmrf/
|
| 主讲教师: |
Uwe Schmidt
|
| 开课单位: |
达姆施塔特理工大学
|
| 开课时间: |
2010-07-19
|
| 课程语种: |
英语
|
| 中文简介: |
马尔可夫随机场（MRFs）是低水平视觉中先验知识的流行和通用概率模型。它们的生成属性很少被检验，而应用特定模型和非概率学习越来越受到关注。在本文中，我们重新审视了MRF的生成方面，并在完全应用中性环境中分析了常见图像先验的质量。通过具有灵活潜力的一般类MRF和高效的Gibbs采样器，我们发现常见的模型无法捕获自然的统计数据图像很好。通过利用有效的采样器来学习如何通过灵活的潜能学习更好的生成MRF，我们可以解决这个问题。我们使用采样计算贝叶斯最小均方误差（MMSE），用这些模型进行图像恢复。这解决了迄今为止具有有限生成性MRF的许多缺点，并且导致相对于最大后验（MAP）估计的性能显着提高。我们证明，将我们学习的生成模型与基于抽样的MMSE估计相结合，可以产生可以与最近的判别方法竞争的优秀应用结果。
|
| 课程简介: |
Markov random fields (MRFs) are popular and generic probabilistic models of prior knowledge in low-level vision. Yet their generative properties are rarely examined, while application-specific models and non-probabilistic learning are gaining increased attention. In this paper we revisit the generative aspects of MRFs, and analyze the quality of common image priors in a fully application-neutral setting. Enabled by a general class of MRFs with flexible potentials and an efficient Gibbs sampler, we find that common models do not capture the statistics of natural images well. We show how to remedy this by exploiting the efficient sampler for learning better generative MRFs based on flexible potentials. We perform image restoration with these models by computing the Bayesian minimum mean squared error estimate (MMSE) using sampling. This addresses a number of shortcomings that have limited generative MRFs so far, and leads to substantially improved performance over maximum a-posteriori (MAP) estimation. We demonstrate that combining our learned generative models with sampling based MMSE estimation yields excellent application results that can compete with recent discriminative methods.
|
| 关 键 词: |
马尔可夫随机场; 采样器; 图像先验
|
| 课程来源: |
视频讲座网
|
| 最后编审: |
2019-03-13：chenxin
|
| 阅读次数: |
87
|
|
图 书 馆