基于语义分割的织锦类自适应风格迁移算法

doi:10.13190/j.jbupt.2020-083

北京邮电大学学报 ›› 2021, Vol. 44 ›› Issue (1): 117-123.doi: 10.13190/j.jbupt.2020-083

基于语义分割的织锦类自适应风格迁移算法

邓筱¹, 徐梦秋², 吴铭², 张闯²

1. 北京邮电大学信息与通信工程学院, 北京 100876;
2. 北京邮电大学人工智能学院, 北京 100876

收稿日期:2020-06-27 出版日期:2021-02-28 发布日期:2021-09-30
通讯作者: 张闯(1975-),男,教授,博士生导师,E-mail:zhangchuang@bupt.edu.cn. E-mail:zhangchuang@bupt.edu.cn
作者简介:邓筱(1999-),女,本科生.
基金资助:
人工智能"教育部-中移动建设项目（MCM20190701）

Adaptive Style Transfer Method of Brocade Crafts Based on Semantic Segmentation

DENG Xiao¹, XU Meng-qiu², WU Ming², ZHANG Chuang²

1. School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2020-06-27 Online:2021-02-28 Published:2021-09-30

摘要/Abstract

摘要： 通过风格迁移的数字化手段可以辅助艺术作品的创作，但由于织锦类手工艺品具有颗粒感线条、块状色彩、前后景纹理区别较大等特点，使用现有风格迁移算法得到的输出图像在视觉上难以达到令人满意的效果.针对上述问题，提出了一种基于语义分割的织锦类自适应感知域风格迁移算法，将语义分割任务和基于自适应感受域的风格迁移算法相结合，并提出新的内容损失和风格损失.此外，为了解决生成结果图像后景中纹理不均匀的问题，在内容图像上增加高斯噪声用于平滑训练过程中生成图像的后景纹理.实验结果表明，所提算法在织锦作品风格迁移任务中的表现优于现有算法.

关键词: 神经风格迁移, 织锦, 语义分割, 自适应感知域

Abstract: Neural style transfer has drawn considerable attention to both academic and art field. However,the existing approaches did not perform so good on brocade style transfer because of its grainy texture and blocky colors which is different from painting. A brocade style transfer approach is proposed that combined semantic segmentation task with adaptive style transfer algorithms by using new content loss and style loss. In addition,in order to solve uneven texture of background in the generated image,Gaussian noise is added to the content image to smoothen background texture during training. It is shown that the proposed approach generates brocade stylization outputs that have high quality as compared with other approaches.

Key words: neural style transfer, brocade crafts, semantic segmentation, adaptive receptive fields

中图分类号:

TP391

邓筱, 徐梦秋, 吴铭, 张闯. 基于语义分割的织锦类自适应风格迁移算法[J]. 北京邮电大学学报, 2021, 44(1): 117-123.

DENG Xiao, XU Meng-qiu, WU Ming, ZHANG Chuang. Adaptive Style Transfer Method of Brocade Crafts Based on Semantic Segmentation[J]. Journal of Beijing University of Posts and Telecommunications, 2021, 44(1): 117-123.

参考文献

[1] 周海燕. 论南京云锦艺术的传承与发展[D]. 南京:东南大学, 2006:25-31.
[2] Gatys L A, Ecker A S, Bethge M. Texture synthesis using convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2015, 28:262-270.
[3] Gatys L A, Ecker A S, Bethge M. A neural algorithm of artistic style[EB/OL]. 2015(2015-08-26)[2020-06-27]. https://arxiv.org/abs/1508.06576.
[4] Jing Yongcheng, Yang Yezhou, Feng Zunlei, et al. Neural style transfer:a review[J]. IEEE Transactions on Visualization and Computer Graphics, 2020, 26(11):3365-3385.
[5] Jing Yongcheng, Liu Yang, Yang Yezhou, et al. Stroke controllable fast style transfer with adaptive receptive fields[C]//Proceedings of the European Conference on Computer Vision(ECCV). Berlin:Springer, 2018:238-254.
[6] Yao Yuan, Ren Jiangqiang, Xie Xuansong, et al. Attention-aware multi-stroke style transfer[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2019:1467-1475.
[7] Gatys L A, Ecker A S, Bethge M. Image style transfer using convolutional neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:2414-2423.
[8] Gatys L A, Ecker A S, Bethge M, et al. Controlling perceptual factors in neural style transfer[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:3985-3993.
[9] Luan Fujun, Paris S, Shechtman E, et al. Deep photo style transfer[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2017:6997-7005.
[10] 李媛琪. 从线条表现的差异浅谈中西方绘画[J]. 西部皮革, 2019, 41(23):101-102. Li Yuanqi. A brief talk on Chinese and western paintings from the difference of line expression[J]. Western Leather, 2019, 41(23):101-102.
[11] 黄明杰. 非物质文化遗产云锦的图案及其保护探究[D]. 重庆:重庆师范大学, 2019:10-15.
[12] 尹晓惠, 郁舒兰. 从形态语义学分析南京云锦图案[J]. 美术教育研究, 2018, 22:20-22. Yin Xiaohui, Yu Shulan. Analysis of Nanjing yunjin pattern from morphological semantics[J]. Art Education Research, 2018, 22:20-22.
[13] Lin T Y, Maire M, Belongie S, et al. Microsoft coco:common objects in context[C]//European Conference on Computer Vision. Berlin:Springer, 2014:740-755.
[14] 王宝林, 宗风英. 南京云锦图典[M]. 南京:南京出版社, 2014.

基于语义分割的织锦类自适应风格迁移算法

Adaptive Style Transfer Method of Brocade Crafts Based on Semantic Segmentation

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	靳梦凡, 黄智濒, 储志强. 复杂环境下多模态指导的点云补全方法[J]. 北京邮电大学学报, 2023, 46(3): 103-108.
[2]	赵海英, 朱会, 侯小刚. 基于改进EMA单元的传统服饰图像语义分割[J]. 北京邮电大学学报, 2022, 45(1): 69-74.