Generating human faces by generative adversarial network
Style transfer is the process of merging the content of one image with the style of another to create a stylized image. In this work, I first study popular style transfer techniques such as Neural Style Transfer and AdaIN. However, current style transfer techniques do not allow fine-level control...
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project (FYP) |
| 语言: | English |
| 出版: |
Nanyang Technological University
2021
|
| 主题: | |
| 在线阅读: | https://hdl.handle.net/10356/153248 |
| _version_ | 1826127041522565120 |
|---|---|
| author | Tao, Weijing |
| author2 | Chen Change Loy |
| author_facet | Chen Change Loy Tao, Weijing |
| author_sort | Tao, Weijing |
| collection | NTU |
| description | Style transfer is the process of merging the content of one image with the style of
another to create a stylized image. In this work, I first study popular style transfer
techniques such as Neural Style Transfer and AdaIN. However, current style transfer
techniques do not allow fine-level control of stylized image features. Next, I study
the state-of-the-art StyleGAN and the network blending algorithm in details and
accomplish style transfer using transfer learning. I provide a total of seven styles for the
process of style transfer, available in different image sizes. In particular, I suggest an
improved model of Toonification by Justin Pinkney, where realistic human textures can
be generated with toonified structural features. In addition, I implement style mixing
on Toonification model which allows control over the high-level fine features of the
generated toonified images. The refined model can be extended to perform real time
arbitrary style transfer where users can easily alter specific features (such as hair colour
and glasses) of their toonified images regardless of their input image size. Finally, I
conclude with discussions on future improvement directions |
| first_indexed | 2024-10-01T07:02:37Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/153248 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:02:37Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1532482021-11-17T01:42:26Z Generating human faces by generative adversarial network Tao, Weijing Chen Change Loy School of Computer Science and Engineering ccloy@ntu.edu.sg Engineering::Computer science and engineering Style transfer is the process of merging the content of one image with the style of another to create a stylized image. In this work, I first study popular style transfer techniques such as Neural Style Transfer and AdaIN. However, current style transfer techniques do not allow fine-level control of stylized image features. Next, I study the state-of-the-art StyleGAN and the network blending algorithm in details and accomplish style transfer using transfer learning. I provide a total of seven styles for the process of style transfer, available in different image sizes. In particular, I suggest an improved model of Toonification by Justin Pinkney, where realistic human textures can be generated with toonified structural features. In addition, I implement style mixing on Toonification model which allows control over the high-level fine features of the generated toonified images. The refined model can be extended to perform real time arbitrary style transfer where users can easily alter specific features (such as hair colour and glasses) of their toonified images regardless of their input image size. Finally, I conclude with discussions on future improvement directions Bachelor of Science in Data Science and Artificial Intelligence 2021-11-17T01:42:26Z 2021-11-17T01:42:26Z 2021 Final Year Project (FYP) Tao, W. (2021). Generating human faces by generative adversarial network. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/153248 https://hdl.handle.net/10356/153248 en SCSE20-0828 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering Tao, Weijing Generating human faces by generative adversarial network |
| title | Generating human faces by generative adversarial network |
| title_full | Generating human faces by generative adversarial network |
| title_fullStr | Generating human faces by generative adversarial network |
| title_full_unstemmed | Generating human faces by generative adversarial network |
| title_short | Generating human faces by generative adversarial network |
| title_sort | generating human faces by generative adversarial network |
| topic | Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/153248 |
| work_keys_str_mv | AT taoweijing generatinghumanfacesbygenerativeadversarialnetwork |