Background preservation for text-guided image editing
The text-guided image editing task aims to manipulate the given image according to another text description while preserving the color, texture and structure information of the text-irrelevant parts of the image. With the development of deep learning and Generative Adversarial Networks (GAN), many G...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/166140 |
| _version_ | 1826121978809942016 |
|---|---|
| author | Huang, Runtao |
| author2 | Lin Guosheng |
| author_facet | Lin Guosheng Huang, Runtao |
| author_sort | Huang, Runtao |
| collection | NTU |
| description | The text-guided image editing task aims to manipulate the given image according to another text description while preserving the color, texture and structure information of the text-irrelevant parts of the image. With the development of deep learning and Generative Adversarial Networks (GAN), many GAN-based methodologies have been proposed to produce very fine-grained high-quality manipulated images according to the text prompt.
However, some state-of-the-art GAN-based methodologies, such as ManiGAN, could not preserve the text-irrelevant backgrounds well. Thus, the objective of this project is to apply the background loss proposed in this paper to improve the background preserving ability of ManiGAN, which is used as the baseline of this project. |
| first_indexed | 2024-10-01T05:40:59Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/166140 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:40:59Z |
| publishDate | 2023 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1661402023-04-21T15:39:02Z Background preservation for text-guided image editing Huang, Runtao Lin Guosheng School of Computer Science and Engineering gslin@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision The text-guided image editing task aims to manipulate the given image according to another text description while preserving the color, texture and structure information of the text-irrelevant parts of the image. With the development of deep learning and Generative Adversarial Networks (GAN), many GAN-based methodologies have been proposed to produce very fine-grained high-quality manipulated images according to the text prompt. However, some state-of-the-art GAN-based methodologies, such as ManiGAN, could not preserve the text-irrelevant backgrounds well. Thus, the objective of this project is to apply the background loss proposed in this paper to improve the background preserving ability of ManiGAN, which is used as the baseline of this project. Bachelor of Engineering (Computer Science) 2023-04-19T02:48:15Z 2023-04-19T02:48:15Z 2023 Final Year Project (FYP) Huang, R. (2023). Background preservation for text-guided image editing. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/166140 https://hdl.handle.net/10356/166140 en SCSE21-0659 10.22002/D1.20098 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision Huang, Runtao Background preservation for text-guided image editing |
| title | Background preservation for text-guided image editing |
| title_full | Background preservation for text-guided image editing |
| title_fullStr | Background preservation for text-guided image editing |
| title_full_unstemmed | Background preservation for text-guided image editing |
| title_short | Background preservation for text-guided image editing |
| title_sort | background preservation for text guided image editing |
| topic | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision |
| url | https://hdl.handle.net/10356/166140 |
| work_keys_str_mv | AT huangruntao backgroundpreservationfortextguidedimageediting |