Continual few-shot patch-based learning for anime-style colorization  

作　　者：Akinobu Maejima Seitaro Shinagawa Hiroyuki Kubo Takuya Funatomi Tatsuo Yotsukura Satoshi Nakamura Yasuhiro Mukaigawa 

机构地区：[1]The Research and Development Division,OLM Digital,Inc.,Advanced Research Group,IMAGICA GROUP,Tokyo 1540023,Japan [2]Division of Information Science,Graduate School of Science and Technology,Nara Institute of Science and Technology,Nara 6300192,Japan [3]Graduate School of Informatics,Chiba University,Chiba 2638522,Japan

出　　处：《Computational Visual Media》2024年第4期705-723,共19页计算可视媒体（英文版）

摘　　要：The automatic colorization of anime line drawings is a challenging problem in production pipelines.Recent advances in deep neural networks have addressed this problem;however,collectingmany images of colorization targets in novel anime work before the colorization process starts leads to chicken-and-egg problems and has become an obstacle to using them in production pipelines.To overcome this obstacle,we propose a new patch-based learning method for few-shot anime-style colorization.The learning method adopts an efficient patch sampling technique with position embedding according to the characteristics of anime line drawings.We also present a continuous learning strategy that continuously updates our colorization model using new samples colorized by human artists.The advantage of our method is that it can learn our colorization model from scratch or pre-trained weights using only a few pre-and post-colorized line drawings that are created by artists in their usual colorization work.Therefore,our method can be easily incorporated within existing production pipelines.We quantitatively demonstrate that our colorizationmethod outperforms state-of-the-art methods.

关 键 词：ANIME COLORIZATION few-shot learning continuous learning strategy 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391.9[自动化与计算机技术—控制科学与工程]