• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of visual communication & image representation >Learning a virtual codec based on deep convolutional neural network to compress image
【24h】

Learning a virtual codec based on deep convolutional neural network to compress image

机译：学习基于深度卷积神经网络的虚拟编解码器以压缩图像

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we propose a standard-compliant image compression framework based on image representation network (IRN) and post-processing neural network (PNN), which are trained by learning a virtual codec network (VCN). Firstly, we use a mixed-resolution image coding considering different types of distortions caused by image compression with different quality factors. Secondly, the VCN is introduced to learn a differentiable soft-projection from the represented image to the post-processed image to resolve the non-differentiable problem of hard quantization. Thirdly, the PNN is used to greatly enhance the quality of decoded images, since standard codecs always result in visually unpleasant blocking artifacts and ringing artifacts. Finally, our framework is trained in an end-to-end manner, whose convolutional kernels of the IRN, PNN and VCN are initialized by pre-training an auto-encoder network. Experimental results verify that our method has higher coding efficiency than the newest image representation-based compression method and many post-processing approaches. (C) 2019 Elsevier Inc. All rights reserved.
机译：在本文中，我们提出了一种基于图像表示网络（IRN）和后处理神经网络（PNN）的符合标准的图像压缩框架，这些框架通过学习虚拟编解码器网络（VCN）进行训练。首先，我们使用混合分辨率图像编码，其中考虑了由具有不同质量因子的图像压缩导致的不同类型的失真。其次，引入VCN以学习从表示图像到后处理图像的可微软投影，以解决硬量化的不可微问题。第三，由于标准编解码器总是导致视觉上令人不快的阻塞伪像和振铃伪像，因此PNN用于大大提高解码图像的质量。最后，我们的框架以端到端的方式进行了训练，其IRN，PNN和VCN的卷积内核是通过预训练自动编码器网络来初始化的。实验结果证明，该方法比最新的基于图像表示的压缩方法和许多后处理方法具有更高的编码效率。 （C）2019 Elsevier Inc.保留所有权利。

著录项

  • 来源
    《Journal of visual communication & image representation》 |2019年第8期|102589.1-102589.11|共11页
  • 作者

    Zhao Lijun; Bai Huihui; Wang Anhong; Zhao Yao;

  • 作者单位

    Beijing Jiaotong Univ Taiyuan Univ Sci & Technol Beijing Key Lab Adv Informat Sci & Network Techno Inst Digital Media & Commun 66 Waliulu Beijing Peoples R China|Beijing Jiaotong Univ Inst Informat Sci 3 Shangyuancun Beijing Peoples R China;

    Beijing Jiaotong Univ Inst Informat Sci 3 Shangyuancun Beijing Peoples R China|Beijing Jiaotong Univ Beijing Key Lab Adv Informat Sci & Network Techno 3 Shangyuancun Beijing Peoples R China;

    Taiyuan Univ Sci & Technol Inst Digital Media & Commun Taiyuan Shanxi Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Image representation; Image compression; Soft-projection; Virtual codec; Post-processing;

    机译：图像表示;图像压缩;软投影;虚拟编解码器;后期处理;

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