StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation

Yunjey Choi; Minje Choi; Munyoung Kim; Jung Woo Ha; Sunghun Kim; Jaegul Choo

doi:10.1109/CVPR.2018.00916

StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation

Yunjey Choi, Minje Choi, Munyoung Kim, Jung Woo Ha, Sunghun Kim, Jaegul Choo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3367 Citations (Scopus)

Abstract

Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. Such a unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network. This leads to StarGAN's superior quality of translated images compared to existing models as well as the novel capability of flexibly translating an input image to any desired target domain. We empirically demonstrate the effectiveness of our approach on a facial attribute transfer and a facial expression synthesis tasks.

Original language	English
Title of host publication	Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Publisher	IEEE Computer Society
Pages	8789-8797
Number of pages	9
ISBN (Electronic)	9781538664209
DOIs	https://doi.org/10.1109/CVPR.2018.00916
Publication status	Published - 2018 Dec 14
Event	31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 - Salt Lake City, United States Duration: 2018 Jun 18 → 2018 Jun 22

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)	1063-6919

Conference

Conference	31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Country/Territory	United States
City	Salt Lake City
Period	18/6/18 → 18/6/22

Bibliographical note

Funding Information:
This work was partially supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIP) (No. NRF2016R1C1B2015924).

Publisher Copyright:
© 2018 IEEE.

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2018.00916

Cite this

Choi, Y., Choi, M., Kim, M., Ha, J. W., Kim, S., & Choo, J. (2018). StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 (pp. 8789-8797). Article 8579014 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society. https://doi.org/10.1109/CVPR.2018.00916

StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation. / Choi, Yunjey; Choi, Minje; Kim, Munyoung et al.
Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society, 2018. p. 8789-8797 8579014 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Choi, Y, Choi, M, Kim, M, Ha, JW, Kim, S & Choo, J 2018, StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018., 8579014, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, pp. 8789-8797, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, United States, 18/6/18. https://doi.org/10.1109/CVPR.2018.00916

Choi Y, Choi M, Kim M, Ha JW, Kim S, Choo J. StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society. 2018. p. 8789-8797. 8579014. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR.2018.00916

Choi, Yunjey ; Choi, Minje ; Kim, Munyoung et al. / StarGAN : Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation. Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society, 2018. pp. 8789-8797 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

@inproceedings{b8760dd8567d42fba7789c7671c15d7c,

title = "StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation",

abstract = "Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. Such a unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network. This leads to StarGAN's superior quality of translated images compared to existing models as well as the novel capability of flexibly translating an input image to any desired target domain. We empirically demonstrate the effectiveness of our approach on a facial attribute transfer and a facial expression synthesis tasks.",

author = "Yunjey Choi and Minje Choi and Munyoung Kim and Ha, \{Jung Woo\} and Sunghun Kim and Jaegul Choo",

note = "Funding Information: This work was partially supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIP) (No. NRF2016R1C1B2015924). Publisher Copyright: {\textcopyright} 2018 IEEE.; 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 ; Conference date: 18-06-2018 Through 22-06-2018",

year = "2018",

month = dec,

day = "14",

doi = "10.1109/CVPR.2018.00916",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "8789--8797",

booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018",

}

TY - GEN

T1 - StarGAN

T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018

AU - Choi, Yunjey

AU - Choi, Minje

AU - Kim, Munyoung

AU - Ha, Jung Woo

AU - Kim, Sunghun

AU - Choo, Jaegul

N1 - Funding Information: This work was partially supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIP) (No. NRF2016R1C1B2015924). Publisher Copyright: © 2018 IEEE.

PY - 2018/12/14

Y1 - 2018/12/14

N2 - Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. Such a unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network. This leads to StarGAN's superior quality of translated images compared to existing models as well as the novel capability of flexibly translating an input image to any desired target domain. We empirically demonstrate the effectiveness of our approach on a facial attribute transfer and a facial expression synthesis tasks.

AB - Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. Such a unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network. This leads to StarGAN's superior quality of translated images compared to existing models as well as the novel capability of flexibly translating an input image to any desired target domain. We empirically demonstrate the effectiveness of our approach on a facial attribute transfer and a facial expression synthesis tasks.

UR - http://www.scopus.com/inward/record.url?scp=85062854894&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2018.00916

DO - 10.1109/CVPR.2018.00916

M3 - Conference contribution

AN - SCOPUS:85062854894

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 8789

EP - 8797

BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018

PB - IEEE Computer Society

Y2 - 18 June 2018 through 22 June 2018

ER -

StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this