首页> 外国专利> Image upscaling system, training method thereof, and image upscaling method

Image upscaling system, training method thereof, and image upscaling method

机译:图像放大系统,其训练方法以及图像放大方法

摘要

An image upscaling system includes at least two convolutional neural network modules and at least one synthesizer. The convolutional neural network module and the synthesizer are alternately connected to one another. The first convolutional neural network module receive an input image and the corresponding supplemental image, generate a first number of the feature images, and output them to the next synthesizer connected thereto. Other convolutional neural network modules each may receive the output image from the previous synthesizer and the corresponding supplemental image, generate a second number of feature images, and output them to the next synthesizer connected thereto, or output them from the image upscaling system. The synthesizer may synthesize every n*n feature images in the received feature image into one feature image and output the resultant third number of feature images to the next convolutional neural network module connected thereto or output them from the image upscaling system.
机译:一种图像放大系统,包括至少两个卷积神经网络模块和至少一个合成器。卷积神经网络模块和合成器彼此交替连接。第一卷积神经网络模块接收输入图像和相应的补充图像,生成第一数量的特征图像,并将它们输出到与其连接的下一个合成器。其他卷积神经网络模块每个都可以接收来自前一合成器的输出图像和相应的补充图像,生成第二数量的特征图像,并将它们输出到与其连接的下一合成器,或者从图像放大系统输出它们。合成器可以将接收到的特征图像中的每n * n个特征图像合成为一个特征图像,并将得到的第三数量的特征图像输出到与其连接的下一个卷积神经网络模块,或者从图像放大系统输出它们。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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