Region-Wise Correspondence Prediction between Manga Line Art Images
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917087939657728 |
|---|---|
| author | Li, Yingxuan Mao, Jiafeng Qiu, Qianru Matsui, Yusuke |
| author_facet | Li, Yingxuan Mao, Jiafeng Qiu, Qianru Matsui, Yusuke |
| contents | Understanding region-wise correspondences between manga line art images is fundamental for high-level manga processing, supporting downstream tasks such as line art colorization and in-between frame generation. Unlike natural images that contain rich visual cues, manga line art consists only of sparse black-and-white strokes, making it challenging to determine which regions correspond across images. In this work, we introduce a new task: predicting region-wise correspondence between raw manga line art images without any annotations. To address this problem, we propose a Transformer-based framework trained on large-scale, automatically generated region correspondences. The model learns to suppress noisy matches and strengthen consistent structural relationships, resulting in robust patch-level feature alignment within and across images. During inference, our method segments each line art and establishes coherent region-level correspondences through edge-aware clustering and region matching. We construct manually annotated benchmarks for evaluation, and experiments across multiple datasets demonstrate both high patch-level accuracy and strong region-level correspondence performance, achieving 78.4-84.4% region-level accuracy. These results highlight the potential of our method for real-world manga and animation applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09501 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Region-Wise Correspondence Prediction between Manga Line Art Images Li, Yingxuan Mao, Jiafeng Qiu, Qianru Matsui, Yusuke Computer Vision and Pattern Recognition Understanding region-wise correspondences between manga line art images is fundamental for high-level manga processing, supporting downstream tasks such as line art colorization and in-between frame generation. Unlike natural images that contain rich visual cues, manga line art consists only of sparse black-and-white strokes, making it challenging to determine which regions correspond across images. In this work, we introduce a new task: predicting region-wise correspondence between raw manga line art images without any annotations. To address this problem, we propose a Transformer-based framework trained on large-scale, automatically generated region correspondences. The model learns to suppress noisy matches and strengthen consistent structural relationships, resulting in robust patch-level feature alignment within and across images. During inference, our method segments each line art and establishes coherent region-level correspondences through edge-aware clustering and region matching. We construct manually annotated benchmarks for evaluation, and experiments across multiple datasets demonstrate both high patch-level accuracy and strong region-level correspondence performance, achieving 78.4-84.4% region-level accuracy. These results highlight the potential of our method for real-world manga and animation applications. |
| title | Region-Wise Correspondence Prediction between Manga Line Art Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.09501 |