[1]周 浩,周先军,邱书畅.下采样迭代和超分辨率重建的图像风格迁移[J].湖北工业大学学报,2020,(1):25-28.
　ZHOU Hao,ZHOU Xianjun,QIU Shuchang.Image Style Transfer Algorithm Based on Downsampling Iterative and Super-Resolution Reconstruction[J].,2020,(1):25-28.
点击复制

下采样迭代和超分辨率重建的图像风格迁移()
分享到：

《湖北工业大学学报》[ISSN:1003-4684/CN:42-1752/Z]

卷:
期数:
2020年第1期
页码:
25-28
栏目:
湖北工业大学学报
出版日期:
2020-02-28

文章信息/Info

Title:
Image Style Transfer Algorithm Based on Downsampling Iterative and Super-Resolution Reconstruction
文章编号:
1003-4684(2020)01-0025-04
作者:
周 浩1; 2;  周先军1; 2;  邱书畅2
1 湖北工业大学湖北省电网智能控制与装备工程技术研究中心， 湖北 武汉 430068；
2 湖北工业大学电气与电子工程学院， 湖北 武汉，430068
Author(s):
ZHOU Hao1; 2;  ZHOU Xianjun1; 2; QIU Shuchang2
1 Hubei Power Grid Intelligent Control and Equipment Engineering, Technology Research Center, Hubei Univ. of Tech., Wuhan 430068, China;
2 School of Electrical and Electronic Engineering, Hubei Univ. of Tech.，Wuhan 430068,China
关键词:
深度学习;  图像风格迁移;  图像下采样;  超分辨率重建
Keywords:
deep learning;  image style transfer; image downsampling;  super-resolution reconstruction
分类号:
TP183
文献标志码:
A
摘要:
提出一种基于下采样迭代和超分辨率重建的图像风格转移算法，即在输入端对输入图像进行下采样，以加速整个图像风格迁移网络的迭代速度，在输出端进行超分辨率的重建，最终输出高分辨率的图像。实验结果表明，该方法减少了整个网络的迭代时间，输出的超分辨率图像也有较好效果。
Abstract:
Based on image iteration, direct iteration takes much time for the image-style migration algorithm. In this paper, an image style transfer algorithm based on downsampling iterative super-resolution reconstruction is proposed, which is to downsample the input image at the input end to accelerate the iterative speed of the entire image style migration network, and to perform super-resolution reconstruction at the output end to output high resolution images. The experimental results show that the method reduces the iteration time of the whole network for content fusion at low resolution, and the reconstructed super-resolution image also has better effect.

参考文献/References:

[1] Gatys L A, Ecker A S, Bethge M. Image style transfer using convolutional neural networks[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）, IEEE, 2016. 2414-2423.[2] Risser E, Wilmot P, Barnes C. Stable and controllable neural texture synthesis and style transfer using histogram losses [EB/OL]. [2019-08-03],https://arxiv.org/abs/1701.08893.
[3] Li Chuan, Wand M. Combining markov random fields and convolutional neural networks for image synthesis [C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition（CVPR）, IEEE, 2016: 2479-2486. 
[4] Johnson J, Alahi A, Li Fei-fei. Perceptual losses for real-time style transfer and super-resolution [C]. European Conference on Computer Vision Springer, 2016: 694-711.
[5] Ulyanov D, Vedaldi A, Lempitsky V. Instance normalization: the missing ingredient for fast stylization [EB/OL]. (2019-08-03), https://arxiv.org/abs/1607.08022.
[6] Dong C, Loy C C, He K, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2016, 38(2):295-307.

相似文献/References:

[1]张 宇,程 玉,陈建峡,等. 基于深度学习的在线推荐学习系统设计与开发[J].湖北工业大学学报,2021,(5):64.
　ZHANG Yu,CHENG Yu,CHEN Jianxia,et al. Design and Development of Online Recommendation Learning System Based on Deep Learning[J].,2021,(1):64.
[2]武明虎,雷常鼎,刘 聪. 改进的轻量级YOLOv4输电线路鸟巢检测方法[J].湖北工业大学学报,2023,(2):11.
　WU Minghu,LEI Changding,LIU Cong. Improved YOLOv4 Transmission Lines Bird’s Nest Detection Method[J].,2023,(1):11.
[3]董　庚１,王焱清１,２,等.基于 ResNet１８网络的油茶果壳籽分选研究[J].湖北工业大学学报,2023,(5):29.
　DONG Gen,WANG Yanqing,SUN Jiwei,et al.Sorting Model of Camellia Fruit Shells and TeaSeeds Based on ResNet18 Network[J].,2023,(1):29.

备注/Memo

备注/Memo:
［收稿日期］ 2019-09-16
［第一作者］ 周   浩(1994-)， 男， 湖北赤壁人，湖北工业大学硕士研究生，研究方向为深度强化学习
更新日期/Last Update: 2020-04-11