Generating human faces by generative adversarial networks
Over the years, computer vision improves significantly. From recognising and understanding what lies underneath an image, we can now generate images by modelling training distribution using generative adversarial network(GAN). Since then, researchers come out with various variants of GAN and ways to...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/139259 |
| _version_ | 1826113154550071296 |
|---|---|
| author | Quek, Chin Wei |
| author2 | Chen Change Loy |
| author_facet | Chen Change Loy Quek, Chin Wei |
| author_sort | Quek, Chin Wei |
| collection | NTU |
| description | Over the years, computer vision improves significantly. From recognising and understanding what lies underneath an image, we can now generate images by modelling training distribution using generative adversarial network(GAN). Since then, researchers come out with various variants of GAN and ways to stabalize GAN training. This results in improved quality of generated image. The application of GAN has sparked the interest of many people. In this project, we first analyse the use of StarGAN, a unified generative adversarial network for multi-domain image-to-image translation task to generate human facial expressions. We also explore the possible use of StarGAN in cartoon character facial expression generation and video generation. |
| first_indexed | 2024-10-01T03:18:33Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/139259 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:18:33Z |
| publishDate | 2020 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1392592020-05-18T07:18:55Z Generating human faces by generative adversarial networks Quek, Chin Wei Chen Change Loy School of Computer Science and Engineering ccloy@ntu.edu.sg Engineering::Computer science and engineering Over the years, computer vision improves significantly. From recognising and understanding what lies underneath an image, we can now generate images by modelling training distribution using generative adversarial network(GAN). Since then, researchers come out with various variants of GAN and ways to stabalize GAN training. This results in improved quality of generated image. The application of GAN has sparked the interest of many people. In this project, we first analyse the use of StarGAN, a unified generative adversarial network for multi-domain image-to-image translation task to generate human facial expressions. We also explore the possible use of StarGAN in cartoon character facial expression generation and video generation. Bachelor of Engineering (Computer Science) 2020-05-18T07:18:55Z 2020-05-18T07:18:55Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/139259 en SCSE19-0113 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering Quek, Chin Wei Generating human faces by generative adversarial networks |
| title | Generating human faces by generative adversarial networks |
| title_full | Generating human faces by generative adversarial networks |
| title_fullStr | Generating human faces by generative adversarial networks |
| title_full_unstemmed | Generating human faces by generative adversarial networks |
| title_short | Generating human faces by generative adversarial networks |
| title_sort | generating human faces by generative adversarial networks |
| topic | Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/139259 |
| work_keys_str_mv | AT quekchinwei generatinghumanfacesbygenerativeadversarialnetworks |