| 李雪瑾,李昕,徐艳杰.基于生成对抗网络的数字图像修复技术[J].电子测量与仪器学报,2019,33(1):40-46 |
| 基于生成对抗网络的数字图像修复技术 |
| Digital image restoration technology based on generative adversarial networks |
| |
| DOI： |
| 中文关键词: 图像修复 深度学习 生成对抗网络 生成模型 损失函数 |
| 英文关键词:image restoration deep learning generative adversarial networks generative model loss function |
| 基金项目: |
|
|
|
|
| 摘要点击次数: 482 |
| 全文下载次数: 0 |
| 中文摘要: |
| 针对破损区域面积大的图像，在现有的图像修复方法中，往往会产生与周围区域不一致的扭曲结构或模糊的纹理。随着深度学习的发展和应用，基于生成对抗网络的方法，通过调节可用数据来生成缺失的内容。对于一个数据集，先将数据集中的样本解析成概率分布中的样本点，利用生成对抗网络快速生成出大量伪造图像，通过搜索最接近的已损坏图像的编码，然后这个编码通过生成模型来推断缺失内容。在此基础上，结合了语义损失函数和感知损失函数，并通过改进激活函数Sigmoid函数扩大了不饱和区域，解决了梯度易消失的问题。通过实验表明，方法成功的预测了图像中大面积缺失区域的信息，并实现了照片的真实感，比先前的方法产生更清晰更连贯的结果。 |
| 英文摘要: |
| For an image with a large damaged area, in the existing image restoration method, a distorted structure or a blurred texture that does not coincide with the surrounding area tends to be generated. With the development and application of deep learning, this paper is based on the method of generative adversarial networks and generates missing content by adjusting the available data. For a data set, the samples in the data set are first parsed into sample points in a probability distribution, a large number of falsified images are quickly generated using the generative adversarial network, the code of the closest damaged image is searched for, and then the code is generated by generating model to infer missing content. On this basis, this paper combines the semantic loss function and the perceptual loss function, and the unsaturated region is enlarged by improving the activation function sigmoid function, and the problem that the gradient easily disappears is solved. Experiments show that the method successfully predicts the information of large areas missing in the image, and realizes the photorealism, producing clearer and more consistent results than previous methods. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
