SKETCH2MANGA: Shaded manga screening from sketch with diffusion models
Author(s)
Author(s)
Xie, M.
Wong, T.-T.
Date Issued
2024
Publisher
IEEE
Related Publication(s)
Proceedings of the IEEE International Conference on Image Processing (ICIP 2024)
Start page
2389
End page
2395
Abstract
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 in generating shaded high-frequency screentones of high-quality. Classic manga screening approaches generally require user input to provide screentone exemplars or a reference manga image. Recent deep learning models enable 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.
SFU Affiliated Publication
Yes
Availability at SFU Library
No database links found.