{"ID":2872236,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.09501","arxiv_id":"2509.09501","title":"Region-Wise Correspondence Prediction between Manga Line Art Images","abstract":"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.","short_abstract":"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 s...","url_abs":"https://arxiv.org/abs/2509.09501","url_pdf":"https://arxiv.org/pdf/2509.09501v3","authors":"[\"Yingxuan Li\",\"Jiafeng Mao\",\"Qianru Qiu\",\"Yusuke Matsui\"]","published":"2025-09-11T14:41:27Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}