| 基于变分方法的超分辨率 |
| |
| 引用本文： | 刘刚,胡臻龙.基于变分方法的超分辨率[J].微电子学与计算机,2012,29(2):159-162. |
| |
| 作者姓名： | 刘刚 胡臻龙 |
| |
| 作者单位： | 1. 长春光学精密机械与物理研究所,吉林长春,130033
2. 浙江越秀外国语学院,浙江绍兴,312000 |
| |
| 基金项目： | 国家“八六三”高科技资助项目 |
| |
| 摘 要： | 基于全变分先验和变分分布.提出一个新颖的超分辨率算法,使用分级的贝叶斯框架,能够同时计算出重建的高分辨率图像和模型参数.本算法利用变分推论给出变量的后验分布近似.因为能够同时估计出模型参数,是自动的过程,无需对参数人工调节.实验结果表明所提算法在重建质量上优于当前主流的算法.
|
| 关 键 词： | 超分辨率 全变分 参数估计 贝叶斯方法 |
A Super-Resolution Algorithm Based on Total Variation |
| |
| LIU Gang,HU Zhen-long.A Super-Resolution Algorithm Based on Total Variation[J].Microelectronics & Computer,2012,29(2):159-162. |
| |
| Authors: | LIU Gang HU Zhen-long |
| |
| Affiliation: | 1 Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033,China; 2 Zhejiang Yuexiu University of Foreign Languages,Shaoxing 312000,China) |
| |
| Abstract: | a novel algorithm for super resolution based on total variation prior and variational distribution approximations is proposed in this paper.We formulate the problem using a hierarchical Bayesian model where the reconstructed high resolution image and the model parameters are estimated simultaneously from the low resolution observations.The algorithm resulting from this formulation utilized variational inference and provides approximations to the posterior distributions of the latent variables.Due to the simultaneous parameter estimation,the algorithm is fully automated so parameter tuning is not required.Experimental results show that the proposed algorithm outperforms some of the state-of-the-art super resolution algorithms. |
| |
| Keywords: | super-resolution total variation parameter estimation Bayesian model |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
