Image color transfer with dense connections generative adversarial networks

Xiao-yu WANG; Yi-feng ZHU; Jin-yang XI; Yao WANG; Jin DUAN

doi:10.3788/YJYXS20203503.0272

您当前的位置：

首页 >

文章列表页 >

Image color transfer with dense connections generative adversarial networks

Image Processing | 更新时间：2020-08-12

- Image color transfer with dense connections generative adversarial networks
- Chinese Journal of Liquid Crystals and Displays Vol. 35, Issue 3, Pages: 272-280(2020)
- 作者机构：
  
  长春理工大学电子信息工程学院, 吉林长春 130022
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20203503.0272
  CLC： TP391
- Received：04 July 2019，
  
  Revised：11 October 2019，
  
  Accepted：11 October 2019，
  
  Published：05 March 2020
- 稿件说明：
移动端阅览
Xiao-yu WANG, Yi-feng ZHU, Jin-yang XI, et al. Image color transfer with dense connections generative adversarial networks[J]. Chinese journal of liquid crystals and displays, 2020, 35(3): 272-280.
DOI：

Xiao-yu WANG, Yi-feng ZHU, Jin-yang XI, et al. Image color transfer with dense connections generative adversarial networks[J]. Chinese journal of liquid crystals and displays, 2020, 35(3): 272-280. DOI： 10.3788/YJYXS20203503.0272.

摘要

针对传统颜色迁移算法在处理图像时存在颜色误传递，色彩不够自然等问题，提出一种基于密集连接生成对抗网络的图像颜色迁移方法。在训练过程中，训练生成网络生成颜色迁移图像。生成网络中的编码层利用密集连接网络跨层连接的优点促进颜色特征重用，加快网络的收敛速度，同时在转换层采用3层残差模块代替原始的两层残差模块更好地组合图像的不同特征。训练判别网络使其辨别原图像与生成的迁移图像间的差别。本文判别网络中用-log函数计算模型损失，加快训练初期更新速度。实验结果表明，与同类模型相比，本文方法结果图像保留更多细节，且能够抑制部分噪声，整体更接近自然图像。

Abstract

Aiming at the problem that the traditional color transfer algorithm has color mis-transmission and unnaturalness as processing images

an image color transfer method based on dense connection generative adversarial network is proposed. During the training process

the training generation network generates the color transfer image. The coding layer in the generated network promotes the reuse of color features and speeds up the convergence rate of the network by using the cross-layer connection of the dense connection network. The conversion layer uses a three-layer residual module instead of the original two-layer residual module to combine different features of the image. The discriminating network is trained to distinguish the difference between the original image and the generated transfer image. The -log function is used to calculate the model loss in the network and speed up the initial update of the training. The experimental results show that the result image of this method retains more details compared with the similar model

can suppress some noise and the whole image is closer to the natural image.

关键词

Keywords

references

E REINHARD , M ADHIKHMIN , B GOOCH , 等 . Color transfer between images . IEEE Computer Graphics and Applications , 2001 . 21 ( 5 ): 34 - 41 . http://d.old.wanfangdata.com.cn/Periodical/jsjfzsjytxxxb200609009 http://d.old.wanfangdata.com.cn/Periodical/jsjfzsjytxxxb200609009 .

TAI Y W, JIA J Y, TANG C K. Local color transfer via probabilistic segmentation by expectation-maximization[C]// Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . San Diego, CA, USA: IEEE, 2005: 747-754.

POULI T, REINHARD E. Progressive histogram reshaping for creative color transfer and tone reproduction[C]// Proceedings of the 8th International Symposium on Non-Photorealistic Animation and Rendering . Annecy, France: ACM, 2010: 81-90.

GUO Y J, LI H, ZHANG W, et al . Multi-source color transfer based on multi-labeled decision tree[C]// Proceedings of the 2008 the 9th International Conference for Young Computer Scientists . Hunan, China: IEEE, 2008: 820-825.

GUPTA R K, CHIA A Y S, RAJAN D, et al . A learning-based approach for automatic image and video colorization[J]. arXiv: 1704.04610, 2012.

YAMAMOTO K, YENDO T, FUJII T, et al . Color correction for multi-camera system by using correspondences[C]// Proceedings of ACM SIGGRAPH 2006 Research Posters . Boston, Massachusetts: ACM, 2006: 213-222.

Y HACOHEN , E SHECHTMAN , D B GOLDMAN , 等 . Non-rigid dense correspondence with applications for image enhancement . ACM Transactions on Graphics , 2011 . 30 ( 4 ): 70 http://cn.bing.com/academic/profile?id=9ac2b4e6bb251d78463ad27d3360b06f&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=9ac2b4e6bb251d78463ad27d3360b06f&encoded=0&v=paper_preview&mkt=zh-cn .

F Z WU , W M DONG , Y KONG , 等 . Content-based colour transfer . Computer Graphics Forum , 2013 . 32 ( 1 ): 190 - 203 . http://d.old.wanfangdata.com.cn/Periodical/nygcxb201418037 http://d.old.wanfangdata.com.cn/Periodical/nygcxb201418037 .

L HE , H R QI , R ZARETZKI . Image color transfer to evoke different emotions based on color combinations . Signal, Image and Video Processing , 2015 . 9 ( 8 ): 1965 - 1973 . http://cn.bing.com/academic/profile?id=7b8e005d5deda481dcfdbf29a483e9bd&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=7b8e005d5deda481dcfdbf29a483e9bd&encoded=0&v=paper_preview&mkt=zh-cn .

GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al . Generative adversarial nets[C]// Proceedings of the 27th International Conference on Neural Information Processing Systems . Montreal, Canada: MIT Press, 2014: 2672-2680.

ODENA A. Semi-supervised learning with generative adversarial networks[EB/OL].[2016-06-05] . https://arxiv.org/pdf/1606.01583.pdf https://arxiv.org/pdf/1606.01583.pdf .

R M H NGUYEN , S J KIM , M S BROWN . Illuminant aware gamut-based color transfer . Computer Graphics Forum , 2014 . 33 ( 7 ): 319 - 328 . http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ0233659906/ http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ0233659906/ .

LEDIG C, THEIS L, HUSZÁR F, et al . Photo-realistic single image super-resolution using a generative adversarial network[C]// Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu, HI, USA: IEEE, 2017: 105-114.

YEH R A, CHEN C, LIM T Y, et al . Semantic image inpainting with deep generative models[C]// Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu, HI, USA: IEEE, 2017: 6882-6890.

ZHU J Y, PARK T, ISOLA P, et al . Unpaired image-to-image translation using cycle-consistent adversarial networks[C]// Proceedings of 2017 IEEE International Conference on Computer Vision . Venice, Italy: IEEE, 2017: 2242-2251.

HUANG G, LIU Z, VAN DER MAATEN L, et al . Densely connected convolutional networks[C]// Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu, HI, USA: IEEE, 2017: 2261-2269.

Y Y SU , H M SUN . Emotion-based color transfer of images using adjustable color combinations . Soft Computing , 2019 . 23 ( 3 ): 1007 - 1020 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=7da54cdd414c462b56efae350c4b0ecc http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=7da54cdd414c462b56efae350c4b0ecc .

G MORI , S BELONGIE , J MALIK . Efficient shape matching using shape contexts . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2005 . 27 ( 11 ): 1832 - 1837 . http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ0214845892/ http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ0214845892/ .

D HASLER , S E SUESSTRUNK . Measuring colorfulness in natural images . SPIE , 2003 . 87 - 95 . http://cn.bing.com/academic/profile?id=82b3cdbd0704786170569ece322e59b2&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=82b3cdbd0704786170569ece322e59b2&encoded=0&v=paper_preview&mkt=zh-cn .

何阳 , 黄玮 , 王新华 , 等 . 稀疏阈值的超分辨率图像重建 . 中国光学 , 2016 . 9 ( 5 ): 532 - 539 . http://d.old.wanfangdata.com.cn/Periodical/zggxyyygxwz201605008 http://d.old.wanfangdata.com.cn/Periodical/zggxyyygxwz201605008 .

Y HE , W HUANG , X H WANG , 等 . Super-resolution image reconstruction based on sparse threshold . Chinese Optics , 2016 . 9 ( 5 ): 532 - 539 . http://d.old.wanfangdata.com.cn/Periodical/zggxyyygxwz201605008 http://d.old.wanfangdata.com.cn/Periodical/zggxyyygxwz201605008 .

朱福珍 , 刘越 , 黄鑫 , 等 . 改进的稀疏表示遥感图像超分辨重建 . 光学精密工程 , 2019 . 27 ( 3 ): 718 - 725 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201903023 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201903023 .

F Z ZHU , Y LIU , X HUANG , 等 . Remote sensing image super-resolution based on improved sparse representation . Optics and Precision Engineering, , 2019 . 27 ( 3 ): 718 - 725 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201903023 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201903023 .

刘超 , 张晓晖 . 超低照度下微光图像的深度卷积自编码网络复原 . 光学精密工程 , 2018 . 26 ( 4 ): 951 - 961 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201804025 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201804025 .

C LIU , X H ZHANG . Deep convolutional autoencoder networks approach to low-light level image restoration under extreme low-light illumination . Optics and Precision Engineering, , 2018 . 26 ( 4 ): 951 - 961 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201804025 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201804025 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Image super-resolution reconstruction using pyramid variance pooling network

Text-to-image generation method based on self-supervised attention and image features fusion

Video anomaly detection based on ensemble generative adversarial networks

Cycle generative adversarial network guided by dual special attention mechanism

Video inpainting based on residual convolution attention network

Related Author

CUI Yun

MENG Xin

LI Yongxin

PENG Yanfei

JIN Haibo

ZHANG Haitao

LIAO Yonghui

GU Jia-cheng

Related Institution

School of Electronic and Information Engineering， Liaoning Technical University

Computer Department, Shantou Polytrchnic

School of Software, Liaoning Technical University

School of Electronic and Electrical Engineering， Shanghai University of Engineering Science

College of Information Engineering, Guangdong University of Technology

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰