Body movement mimic - Video-based human body motion transfer
MagicAnimate is a powerful tool for generating videos from low-resolution inputs. However, the quality of the output videos can be compromised due to the complexity of different driving poses and the limitations of the model. This project proposes a pipeline to enhance the output videos from MagicAn...
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project (FYP) |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/177769 |
_version_ | 1811690619775483904 |
---|---|
author | Wang, Sunmeng |
author2 | Cham Tat Jen |
author_facet | Cham Tat Jen Wang, Sunmeng |
author_sort | Wang, Sunmeng |
collection | NTU |
description | MagicAnimate is a powerful tool for generating videos from low-resolution inputs. However, the quality of the output videos can be compromised due to the complexity of different driving poses and the limitations of the model. This project proposes a pipeline to enhance the output videos from MagicAnimate by integrating face restoration and face swapping techniques, as well as to provide an updated UI for user convenience. |
first_indexed | 2024-10-01T06:06:53Z |
format | Final Year Project (FYP) |
id | ntu-10356/177769 |
institution | Nanyang Technological University |
language | English |
last_indexed | 2024-10-01T06:06:53Z |
publishDate | 2024 |
publisher | Nanyang Technological University |
record_format | dspace |
spelling | ntu-10356/1777692024-05-31T15:39:02Z Body movement mimic - Video-based human body motion transfer Wang, Sunmeng Cham Tat Jen School of Computer Science and Engineering ASTJCham@ntu.edu.sg Computer and Information Science Artificial intelligence MagicAnimate is a powerful tool for generating videos from low-resolution inputs. However, the quality of the output videos can be compromised due to the complexity of different driving poses and the limitations of the model. This project proposes a pipeline to enhance the output videos from MagicAnimate by integrating face restoration and face swapping techniques, as well as to provide an updated UI for user convenience. Bachelor's degree 2024-05-31T03:54:57Z 2024-05-31T03:54:57Z 2024 Final Year Project (FYP) Wang, S. (2024). Body movement mimic - Video-based human body motion transfer. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/177769 https://hdl.handle.net/10356/177769 en application/pdf Nanyang Technological University |
spellingShingle | Computer and Information Science Artificial intelligence Wang, Sunmeng Body movement mimic - Video-based human body motion transfer |
title | Body movement mimic - Video-based human body motion transfer |
title_full | Body movement mimic - Video-based human body motion transfer |
title_fullStr | Body movement mimic - Video-based human body motion transfer |
title_full_unstemmed | Body movement mimic - Video-based human body motion transfer |
title_short | Body movement mimic - Video-based human body motion transfer |
title_sort | body movement mimic video based human body motion transfer |
topic | Computer and Information Science Artificial intelligence |
url | https://hdl.handle.net/10356/177769 |
work_keys_str_mv | AT wangsunmeng bodymovementmimicvideobasedhumanbodymotiontransfer |