• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Signal Image Processing and Communication >Super-resolution reconstruction of image based on generative adversarial network with attention module
【24h】

Super-resolution reconstruction of image based on generative adversarial network with attention module

机译：基于生成对抗网络与注意模块的图像超分辨率重构

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In order to solve the problems of unstable training and texture blurring of generated images, we proposed a generative adversarial network combining residual and attention block. The attention module is added to the network, which reduces the dependence on the network depth and reduces the depth of the model. The dense connection in the residual module can extract richer image details. The number of parameters is reduced and the calculation efficiency is greatly improved. Generative adversarial network is used to further improve the texture details of the image. Generator loss functions include a content loss, a perceptual loss, a texture loss and an adversarial loss. The texture loss is used to enhance the matching degree of local information, and the perceptual loss is used to obtain more detailed features by using the feature information before an activation layer. The experimental results show that the peak signal to noise ratio is 32.10 dB, and the structural similarity is 0.92. Compared with bicubic, SRCNN, VDSR and SRGAN, the proposed algorithm improves the texture details of reconstructed images.
机译：为了解决生成图像的不稳定训练和纹理模糊的问题，我们提出了一种组合残差和注意力块的生成的对抗性网络。注意模块被添加到网络中，这减少了对网络深度的依赖性并减少了模型的深度。残余模块中的密集连接可以提取更丰富的图像细节。减少了参数的数量，并大大提高了计算效率。生成的对抗网络用于进一步改善图像的纹理细节。发电机损耗功能包括内容损失，感知损失，纹理损失和对抗性损失。纹理损耗用于增强局部信息的匹配程度，并且感知损失用于通过在激活层之前使用特征信息来获得更详细的特征。实验结果表明，峰值信噪比为32.10dB，结构相似性为0.92。与双臂，SRCNN，VDSR和SRAN相比，所提出的算法改善了重建图像的纹理细节。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号