Sketch2Manga: Shaded Manga Screening from Sketch with Diffusion Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914712944377856 |
|---|---|
| author | Lin, Jian Liu, Xueting Li, Chengze Xie, Minshan Wong, Tien-Tsin |
| author_facet | Lin, Jian Liu, Xueting Li, Chengze Xie, Minshan Wong, Tien-Tsin |
| contents | While manga is a popular entertainment form, creating manga is tedious, especially adding screentones to the created sketch, namely manga screening. Unfortunately, there is no existing method that tailors for automatic manga screening, probably due to the difficulty of generating high-quality shaded high-frequency screentones. The classic manga screening approaches generally require user input to provide screentone exemplars or a reference manga image. The recent deep learning models enables the automatic generation by learning from a large-scale dataset. However, the state-of-the-art models still fail to generate high-quality shaded screentones due to the lack of a tailored model and high-quality manga training data. In this paper, we propose a novel sketch-to-manga framework that first generates a color illustration from the sketch and then generates a screentoned manga based on the intensity guidance. Our method significantly outperforms existing methods in generating high-quality manga with shaded high-frequency screentones. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08266 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sketch2Manga: Shaded Manga Screening from Sketch with Diffusion Models Lin, Jian Liu, Xueting Li, Chengze Xie, Minshan Wong, Tien-Tsin Computer Vision and Pattern Recognition Graphics I.4.6; I.3.3; I.3.8 While manga is a popular entertainment form, creating manga is tedious, especially adding screentones to the created sketch, namely manga screening. Unfortunately, there is no existing method that tailors for automatic manga screening, probably due to the difficulty of generating high-quality shaded high-frequency screentones. The classic manga screening approaches generally require user input to provide screentone exemplars or a reference manga image. The recent deep learning models enables the automatic generation by learning from a large-scale dataset. However, the state-of-the-art models still fail to generate high-quality shaded screentones due to the lack of a tailored model and high-quality manga training data. In this paper, we propose a novel sketch-to-manga framework that first generates a color illustration from the sketch and then generates a screentoned manga based on the intensity guidance. Our method significantly outperforms existing methods in generating high-quality manga with shaded high-frequency screentones. |
| title | Sketch2Manga: Shaded Manga Screening from Sketch with Diffusion Models |
| topic | Computer Vision and Pattern Recognition Graphics I.4.6; I.3.3; I.3.8 |
| url | https://arxiv.org/abs/2403.08266 |