An interactive and generative approach for Chinese Shanshui painting document

Aven Le Zhou; Qiu Feng Wang; Kaizhu Huang; Cheng Hung Lo

doi:10.1109/ICDAR.2019.00136

An interactive and generative approach for Chinese Shanshui painting document

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

30 Citations (Scopus)

Abstract

Chinese Shanshui is a landscape painting document mainly drawing mountain and water, which is popular in Chinese culture. However, it is very challenging to create this by general people. In this paper, we propose an interactive and generative approach to automatically generate the Chinese Shanshui painting documents based on users' input, where the users only need to sketch simple lines to represent their ideal landscape without any professional Shanshui painting skills. This sketch-to-Shanshui translation is optimized by the model of cycle Generative Adversarial Networks (GAN). To evaluate the proposed approach, we collected a large set of both sketch data and Chinese Shanshui painting data to train the model of cycle-GAN, and developed an interactive system called Shanshui-DaDA (i.e., Design and Draw with AI) to generate Chinese Shanshui painting documents in real-time. The experimental results show that this system can generate satisfied Chinese Shanshui painting documents by general users.

Original language	English
Title of host publication	Proceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
Publisher	IEEE Computer Society
Pages	819-824
Number of pages	6
ISBN (Electronic)	9781728128610
DOIs	https://doi.org/10.1109/ICDAR.2019.00136
Publication status	Published - Sept 2019
Event	15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019 - Sydney, Australia Duration: 20 Sept 2019 → 25 Sept 2019

Publication series

Name	Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
ISSN (Print)	1520-5363

Conference

Conference	15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019
Country/Territory	Australia
City	Sydney
Period	20/09/19 → 25/09/19

Keywords

Chinese Shanshui
Generative Adversarial Networks
Image-to-image Translation
Interactive system
Sketch-to-Shanshui Translation

Access to Document

10.1109/ICDAR.2019.00136

Cite this

Zhou, A. L., Wang, Q. F., Huang, K., & Lo, C. H. (2019). An interactive and generative approach for Chinese Shanshui painting document. In Proceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019 (pp. 819-824). Article 8978182 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR). IEEE Computer Society. https://doi.org/10.1109/ICDAR.2019.00136

@inproceedings{661295a475b443328ffb6aa96a4e39ef,

title = "An interactive and generative approach for Chinese Shanshui painting document",

abstract = "Chinese Shanshui is a landscape painting document mainly drawing mountain and water, which is popular in Chinese culture. However, it is very challenging to create this by general people. In this paper, we propose an interactive and generative approach to automatically generate the Chinese Shanshui painting documents based on users' input, where the users only need to sketch simple lines to represent their ideal landscape without any professional Shanshui painting skills. This sketch-to-Shanshui translation is optimized by the model of cycle Generative Adversarial Networks (GAN). To evaluate the proposed approach, we collected a large set of both sketch data and Chinese Shanshui painting data to train the model of cycle-GAN, and developed an interactive system called Shanshui-DaDA (i.e., Design and Draw with AI) to generate Chinese Shanshui painting documents in real-time. The experimental results show that this system can generate satisfied Chinese Shanshui painting documents by general users.",

keywords = "Chinese Shanshui, Generative Adversarial Networks, Image-to-image Translation, Interactive system, Sketch-to-Shanshui Translation",

author = "Zhou, \{Aven Le\} and Wang, \{Qiu Feng\} and Kaizhu Huang and Lo, \{Cheng Hung\}",

note = "Funding Information: ACKNOWLEDGMENT This work is supported by the National Natural Science Foundation of China under grants no.61876154 and 61876155, Natural Science Foundation of Jiangsu Higher Education Institutions of China no.17KJB520041, Suzhou Science and Technology Program no.SYG201838, and CCF-Tencent Open Research Fund RAGR20180109. Publisher Copyright: {\textcopyright} 2019 IEEE.; 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019 ; Conference date: 20-09-2019 Through 25-09-2019",

year = "2019",

month = sep,

doi = "10.1109/ICDAR.2019.00136",

language = "English",

series = "Proceedings of the International Conference on Document Analysis and Recognition, ICDAR",

publisher = "IEEE Computer Society",

pages = "819--824",

booktitle = "Proceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019",

}

Zhou, AL , Wang, QF, Huang, K & Lo, CH 2019, An interactive and generative approach for Chinese Shanshui painting document. in Proceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019., 8978182, Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, IEEE Computer Society, pp. 819-824, 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019, Sydney, Australia, 20/09/19. https://doi.org/10.1109/ICDAR.2019.00136

An interactive and generative approach for Chinese Shanshui painting document. / Zhou, Aven Le ; Wang, Qiu Feng; Huang, Kaizhu et al.
Proceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019. IEEE Computer Society, 2019. p. 819-824 8978182 (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - An interactive and generative approach for Chinese Shanshui painting document

AU - Zhou, Aven Le

AU - Wang, Qiu Feng

AU - Huang, Kaizhu

AU - Lo, Cheng Hung

N1 - Funding Information: ACKNOWLEDGMENT This work is supported by the National Natural Science Foundation of China under grants no.61876154 and 61876155, Natural Science Foundation of Jiangsu Higher Education Institutions of China no.17KJB520041, Suzhou Science and Technology Program no.SYG201838, and CCF-Tencent Open Research Fund RAGR20180109. Publisher Copyright: © 2019 IEEE.

PY - 2019/9

Y1 - 2019/9

N2 - Chinese Shanshui is a landscape painting document mainly drawing mountain and water, which is popular in Chinese culture. However, it is very challenging to create this by general people. In this paper, we propose an interactive and generative approach to automatically generate the Chinese Shanshui painting documents based on users' input, where the users only need to sketch simple lines to represent their ideal landscape without any professional Shanshui painting skills. This sketch-to-Shanshui translation is optimized by the model of cycle Generative Adversarial Networks (GAN). To evaluate the proposed approach, we collected a large set of both sketch data and Chinese Shanshui painting data to train the model of cycle-GAN, and developed an interactive system called Shanshui-DaDA (i.e., Design and Draw with AI) to generate Chinese Shanshui painting documents in real-time. The experimental results show that this system can generate satisfied Chinese Shanshui painting documents by general users.

AB - Chinese Shanshui is a landscape painting document mainly drawing mountain and water, which is popular in Chinese culture. However, it is very challenging to create this by general people. In this paper, we propose an interactive and generative approach to automatically generate the Chinese Shanshui painting documents based on users' input, where the users only need to sketch simple lines to represent their ideal landscape without any professional Shanshui painting skills. This sketch-to-Shanshui translation is optimized by the model of cycle Generative Adversarial Networks (GAN). To evaluate the proposed approach, we collected a large set of both sketch data and Chinese Shanshui painting data to train the model of cycle-GAN, and developed an interactive system called Shanshui-DaDA (i.e., Design and Draw with AI) to generate Chinese Shanshui painting documents in real-time. The experimental results show that this system can generate satisfied Chinese Shanshui painting documents by general users.

KW - Chinese Shanshui

KW - Generative Adversarial Networks

KW - Image-to-image Translation

KW - Interactive system

KW - Sketch-to-Shanshui Translation

UR - https://www.scopus.com/pages/publications/85079851174

U2 - 10.1109/ICDAR.2019.00136

DO - 10.1109/ICDAR.2019.00136

M3 - Conference Proceeding

AN - SCOPUS:85079851174

T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

SP - 819

EP - 824

BT - Proceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019

PB - IEEE Computer Society

T2 - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019

Y2 - 20 September 2019 through 25 September 2019

ER -

Zhou AL , Wang QF, Huang K, Lo CH. An interactive and generative approach for Chinese Shanshui painting document. In Proceedings - 15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019. IEEE Computer Society. 2019. p. 819-824. 8978182. (Proceedings of the International Conference on Document Analysis and Recognition, ICDAR). doi: 10.1109/ICDAR.2019.00136

An interactive and generative approach for Chinese Shanshui painting document

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Shanshui Journey: Using AI to Reproduce the Experience of Chinese Literati Ink Paintings

Cite this