Automated colorization of animated characters
This project undertakes the task of automating colorization in animations by exploring Frame-by-Frame Prediction Models and T-pose Reference-based Prediction approaches. Emphasizing the imperatives of reducing manual labor burden on Digital Painters, the study advocates for the adoption of innovativ...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/175784 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-175784 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1757842024-05-10T15:40:43Z Automated colorization of animated characters Lin, Jiajun Chen Change Loy School of Computer Science and Engineering ccloy@ntu.edu.sg Computer and Information Science This project undertakes the task of automating colorization in animations by exploring Frame-by-Frame Prediction Models and T-pose Reference-based Prediction approaches. Emphasizing the imperatives of reducing manual labor burden on Digital Painters, the study advocates for the adoption of innovative frameworks. The analysis delves into Frame-by-Frame Prediction Models, analysing performance of Segment Matching and Optical Flow through RAFT, each presenting its own merits and drawbacks. Additionally, image segmentation models, including PSANet and PSPNet, are investigated for possible integration into Segment Matching Models to achieve T-pose Reference-based Prediction. Moving forward, further research and development are crucial to enhance image segmentation methods and seamlessly integrate them into colorization workflows, ushering in automation in animation production. Bachelor's degree 2024-05-07T01:23:25Z 2024-05-07T01:23:25Z 2024 Final Year Project (FYP) Lin, J. (2024). Automated colorization of animated characters. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175784 https://hdl.handle.net/10356/175784 en application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Computer and Information Science |
spellingShingle |
Computer and Information Science Lin, Jiajun Automated colorization of animated characters |
description |
This project undertakes the task of automating colorization in animations by exploring Frame-by-Frame Prediction Models and T-pose Reference-based Prediction approaches. Emphasizing the imperatives of reducing manual labor burden on Digital Painters, the study advocates for the adoption of innovative frameworks. The analysis delves into Frame-by-Frame Prediction Models, analysing performance of Segment Matching and Optical Flow through RAFT, each presenting its own merits and drawbacks. Additionally, image segmentation models, including PSANet and PSPNet, are investigated for possible integration into Segment Matching Models to achieve T-pose Reference-based Prediction. Moving forward, further research and development are crucial to enhance image segmentation methods and seamlessly integrate them into colorization workflows, ushering in automation in animation production. |
author2 |
Chen Change Loy |
author_facet |
Chen Change Loy Lin, Jiajun |
format |
Final Year Project |
author |
Lin, Jiajun |
author_sort |
Lin, Jiajun |
title |
Automated colorization of animated characters |
title_short |
Automated colorization of animated characters |
title_full |
Automated colorization of animated characters |
title_fullStr |
Automated colorization of animated characters |
title_full_unstemmed |
Automated colorization of animated characters |
title_sort |
automated colorization of animated characters |
publisher |
Nanyang Technological University |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/175784 |
_version_ |
1814047434618175488 |