Asymmetric Two-Stage CycleGAN for Generation of Faces With Shadow Puppet Style
In this paper, we study the problem of cross-domain image-to-image transformation from real faces to faces with shadow puppet style. Our aim is to make target images retain the salient features of real faces and capture the artistic style of shadow puppet faces. This task involves dual changes of co...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9992216/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582326686580736 |
|---|---|
| author | Jingzhou Huang Xiaofang Huang Taixiang Zhang Jingchao Jiang Houpan Zhou |
| author_facet | Jingzhou Huang Xiaofang Huang Taixiang Zhang Jingchao Jiang Houpan Zhou |
| author_sort | Jingzhou Huang |
| collection | DOAJ |
| description | In this paper, we study the problem of cross-domain image-to-image transformation from real faces to faces with shadow puppet style. Our aim is to make target images retain the salient features of real faces and capture the artistic style of shadow puppet faces. This task involves dual changes of contents and geometric structures to the source image, and the target distribution is a transitional distribution, that cannot be solved by existing solutions. We propose a new CycleGAN-based scheme that extends the transformation of two image domains to that of three domains. We adopt a two-stage generation strategy in the forward transformation and urge the generator of the first stage to learn the target distribution. To this end, we set up a discriminator for the generator to guide its generation. We also present a multiple contrastive training strategy to address the problem of difficulty in training the discriminator, because there is no way to obtain real samples from the target domain. The experimental results show that our scheme is effective and that the target generator can produce intermediate images that meet the requirements. |
| format | Article |
| id | doaj-art-a7bbe031e90e4357ac4bf3e77e637387 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a7bbe031e90e4357ac4bf3e77e6373872025-01-30T00:01:23ZengIEEEIEEE Access2169-35362022-01-011013286313287410.1109/ACCESS.2022.32307599992216Asymmetric Two-Stage CycleGAN for Generation of Faces With Shadow Puppet StyleJingzhou Huang0https://orcid.org/0000-0001-6413-556XXiaofang Huang1https://orcid.org/0000-0002-1210-7580Taixiang Zhang2Jingchao Jiang3Houpan Zhou4School of Automation, Hangzhou Dianzi University, Hangzhou, ChinaCollege of Art and Communication, China Jiliang University, Hangzhou, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou, ChinaIn this paper, we study the problem of cross-domain image-to-image transformation from real faces to faces with shadow puppet style. Our aim is to make target images retain the salient features of real faces and capture the artistic style of shadow puppet faces. This task involves dual changes of contents and geometric structures to the source image, and the target distribution is a transitional distribution, that cannot be solved by existing solutions. We propose a new CycleGAN-based scheme that extends the transformation of two image domains to that of three domains. We adopt a two-stage generation strategy in the forward transformation and urge the generator of the first stage to learn the target distribution. To this end, we set up a discriminator for the generator to guide its generation. We also present a multiple contrastive training strategy to address the problem of difficulty in training the discriminator, because there is no way to obtain real samples from the target domain. The experimental results show that our scheme is effective and that the target generator can produce intermediate images that meet the requirements.https://ieeexplore.ieee.org/document/9992216/Image-to-image transformationmultiple contrastive trainingshadow puppet styletransitional distribution |
| spellingShingle | Jingzhou Huang Xiaofang Huang Taixiang Zhang Jingchao Jiang Houpan Zhou Asymmetric Two-Stage CycleGAN for Generation of Faces With Shadow Puppet Style IEEE Access Image-to-image transformation multiple contrastive training shadow puppet style transitional distribution |
| title | Asymmetric Two-Stage CycleGAN for Generation of Faces With Shadow Puppet Style |
| title_full | Asymmetric Two-Stage CycleGAN for Generation of Faces With Shadow Puppet Style |
| title_fullStr | Asymmetric Two-Stage CycleGAN for Generation of Faces With Shadow Puppet Style |
| title_full_unstemmed | Asymmetric Two-Stage CycleGAN for Generation of Faces With Shadow Puppet Style |
| title_short | Asymmetric Two-Stage CycleGAN for Generation of Faces With Shadow Puppet Style |
| title_sort | asymmetric two stage cyclegan for generation of faces with shadow puppet style |
| topic | Image-to-image transformation multiple contrastive training shadow puppet style transitional distribution |
| url | https://ieeexplore.ieee.org/document/9992216/ |
| work_keys_str_mv | AT jingzhouhuang asymmetrictwostagecycleganforgenerationoffaceswithshadowpuppetstyle AT xiaofanghuang asymmetrictwostagecycleganforgenerationoffaceswithshadowpuppetstyle AT taixiangzhang asymmetrictwostagecycleganforgenerationoffaceswithshadowpuppetstyle AT jingchaojiang asymmetrictwostagecycleganforgenerationoffaceswithshadowpuppetstyle AT houpanzhou asymmetrictwostagecycleganforgenerationoffaceswithshadowpuppetstyle |