|
|||||
|
|
| 融合深度图像先验的全变差图像着色算法 | |
| 引用本文： | 张玺,金正猛,姜亚琴. 融合深度图像先验的全变差图像着色算法[J]. 系统工程与电子技术, 2022, 44(2): 385-393. DOI: 10.12305/j.issn.1001-506X.2022.02.04 |
| 作者姓名： | 张玺 金正猛 姜亚琴 |
| 作者单位： | 南京邮电大学理学院, 江苏 南京 210023 |
| 基金项目： | 国家自然科学基金(11771005)资助课题。 |
| 摘 要： | 提出了融合深度图像先验的全变差(total variation,TV)图像着色模型,在即插即用(plug-and-play,PnP)框架下,结合交替方向乘子法(alternating direction method of multipliers,ADMM),设计出相应的数值求解算法,并给出该算法的收敛性结果.数值实验... |
| 关 键 词： | 图像着色 耦合全变差 卷积神经网络 即插即用框架 交替方向乘子算法 |
| 收稿时间： | 2021-03-02 |
Total variation algorithm with depth image priors for image colorization |
|
| ZHANG Xi,JIN Zhengmeng,JIANG Yaqin. Total variation algorithm with depth image priors for image colorization[J]. System Engineering and Electronics, 2022, 44(2): 385-393. DOI: 10.12305/j.issn.1001-506X.2022.02.04 | |
| Authors: | ZHANG Xi JIN Zhengmeng JIANG Yaqin |
| Affiliation: | Shool of Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China |
| Abstract: | In this paper,we propose a total variation(TV)model with depth image priors for image colorization.Under the plug-and-play(PnP)framework,we design the numerical algorithm to solve the model by incorporating the alternating direction method of multipliers(ADMM),and give the convergence result of the algorithm.The experimental results show that the model can effectively integrate the edge capture function of coupled TV and the detail capture function of convolutional neural network(CNN),and also can achieve a large scale effective coloring for structural images and multi textures detailed images. |
| Keywords: | image coloring coupled total variation(TV) convolutional neural network(CNN) plug-and-play(PnP)framework alternating direction method of multipliers(ADMM) |
| 本文献已被 维普 等数据库收录！ | |
| 点击此处可从《系统工程与电子技术》浏览原始摘要信息 | |
| 点击此处可从《系统工程与电子技术》下载全文 | |