Advancing Sequential Manga Colorization for AR Through Data Synthesis
Manga colorization in augmented reality (AR) environments presents unique challenges, particularly when colorizing manga pages captured in photos under various real-world conditions. Testing models in AR settings for manga colorization has been a significant challenge, primarily because of the absen...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10830475/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536175640150016 |
|---|---|
| author | Maksim Golyadkin Sergey Saraev Ilya Makarov |
| author_facet | Maksim Golyadkin Sergey Saraev Ilya Makarov |
| author_sort | Maksim Golyadkin |
| collection | DOAJ |
| description | Manga colorization in augmented reality (AR) environments presents unique challenges, particularly when colorizing manga pages captured in photos under various real-world conditions. Testing models in AR settings for manga colorization has been a significant challenge, primarily because of the absence of suitable datasets tailored for this task. To address this, we propose a benchmark for evaluating existing colorization models. We first collected a relatively small dataset of manga book photos taken in settings suitable for AR applications. Then, we developed a method that leverages a pretrained diffusion model to generate synthetic photos from scans of manga pages. Using large datasets of manga scans, we created an extensive synthetic dataset. Combining both real and synthetic data, we established a comprehensive benchmark for manga colorization in AR scenarios. We tested existing models for natural image and manga colorization on this benchmark. As a result, our evaluation showed that current models are not well-suited for AR-based colorization tasks, indicating a need for further improvement. |
| format | Article |
| id | doaj-art-5f8001ac13b74d8788f07db08250db69 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-5f8001ac13b74d8788f07db08250db692025-01-15T00:03:27ZengIEEEIEEE Access2169-35362025-01-01137526753710.1109/ACCESS.2025.352688210830475Advancing Sequential Manga Colorization for AR Through Data SynthesisMaksim Golyadkin0https://orcid.org/0000-0002-0679-6981Sergey Saraev1Ilya Makarov2https://orcid.org/0000-0002-3308-8825Artificial Intelligence Research Institute (AIRI), Moscow, RussiaAI Talent Hub, ITMO University, Saint Petersburg, RussiaArtificial Intelligence Research Institute (AIRI), Moscow, RussiaManga colorization in augmented reality (AR) environments presents unique challenges, particularly when colorizing manga pages captured in photos under various real-world conditions. Testing models in AR settings for manga colorization has been a significant challenge, primarily because of the absence of suitable datasets tailored for this task. To address this, we propose a benchmark for evaluating existing colorization models. We first collected a relatively small dataset of manga book photos taken in settings suitable for AR applications. Then, we developed a method that leverages a pretrained diffusion model to generate synthetic photos from scans of manga pages. Using large datasets of manga scans, we created an extensive synthetic dataset. Combining both real and synthetic data, we established a comprehensive benchmark for manga colorization in AR scenarios. We tested existing models for natural image and manga colorization on this benchmark. As a result, our evaluation showed that current models are not well-suited for AR-based colorization tasks, indicating a need for further improvement.https://ieeexplore.ieee.org/document/10830475/Manga colorizationaugmented realitydatasetbenchmark |
| spellingShingle | Maksim Golyadkin Sergey Saraev Ilya Makarov Advancing Sequential Manga Colorization for AR Through Data Synthesis IEEE Access Manga colorization augmented reality dataset benchmark |
| title | Advancing Sequential Manga Colorization for AR Through Data Synthesis |
| title_full | Advancing Sequential Manga Colorization for AR Through Data Synthesis |
| title_fullStr | Advancing Sequential Manga Colorization for AR Through Data Synthesis |
| title_full_unstemmed | Advancing Sequential Manga Colorization for AR Through Data Synthesis |
| title_short | Advancing Sequential Manga Colorization for AR Through Data Synthesis |
| title_sort | advancing sequential manga colorization for ar through data synthesis |
| topic | Manga colorization augmented reality dataset benchmark |
| url | https://ieeexplore.ieee.org/document/10830475/ |
| work_keys_str_mv | AT maksimgolyadkin advancingsequentialmangacolorizationforarthroughdatasynthesis AT sergeysaraev advancingsequentialmangacolorizationforarthroughdatasynthesis AT ilyamakarov advancingsequentialmangacolorizationforarthroughdatasynthesis |