• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Yin, Wenbin (Yin, Wenbin.) | Shi, Yunhui (Shi, Yunhui.) (学者:施云惠) | Zuo, Wangmeng (Zuo, Wangmeng.) | Fan, Xiaopeng (Fan, Xiaopeng.)

收录:

EI SCIE

摘要:

Deep learning has achieved a preliminary success in image compression due to the ability to learn the nonlinear spaces with compact features that training samples belong to. Unfortunately, it is not straightforward for the network based image compression methods to code multiple highly related images. In this paper, we propose a co-prediction based image compression (CPIC) which uses the multi-stream autoencoders to collaboratively code the multiple highly correlated images by enforcing the co-reference constraint on the multi-stream features. Patch samples fed into the multi-stream autoencoder, are generated through corresponding patch matching under permutation, which helps the autoencoder to learn the relationship among corresponding patches from the correlated images. Each stream network consists of encoder, decoder, importance map network and binarizer. In order to guide the allocation of local bit rate of the binary features, the important map network is employed to guarantee the compactness of learned features. A proxy function is used to make the binary operation for the code layer of the autoencoder differentiable. Finally, the network optimization is formulated as a rate distortion optimization. Experimental results prove that the proposed compression method outperforms JPEG2000 up to 1.5 dB in terms of PSNR.

关键词:

Autoencoder Convolutional codes correlated images Decoding Image coding image compression Image reconstruction multi-stream networks Optimization rate distortion optimization Transform coding Transforms

作者机构:

  • [ 1 ] [Yin, Wenbin]Harbin Inst Technol, Dept Comp Sci & Technol, Harbin 150001, Peoples R China
  • [ 2 ] [Zuo, Wangmeng]Harbin Inst Technol, Dept Comp Sci & Technol, Harbin 150001, Peoples R China
  • [ 3 ] [Fan, Xiaopeng]Harbin Inst Technol, Dept Comp Sci & Technol, Harbin 150001, Peoples R China
  • [ 4 ] [Shi, Yunhui]Beijing Univ Technol, BJUT Fac Informat Technol, Beijing 100124, Peoples R China
  • [ 5 ] [Fan, Xiaopeng]Peng Cheng Lab, Shenzhen 518066, Peoples R China

通讯作者信息:

  • [Fan, Xiaopeng]Harbin Inst Technol, Dept Comp Sci & Technol, Harbin 150001, Peoples R China

查看成果更多字段

相关关键词:

相关文章:

来源 :

IEEE TRANSACTIONS ON MULTIMEDIA

ISSN: 1520-9210

年份: 2020

期: 8

卷: 22

页码: 1917-1928

7 . 3 0 0

JCR@2022

ESI学科: COMPUTER SCIENCE;

ESI高被引阀值:34

JCR分区:1

被引次数:

WoS核心集被引频次: 4

SCOPUS被引频次: 4

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 2

归属院系:

在线人数/总访问数:150/3603168
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司