“Anime Colorization Using Segment Matching With Candidate Colors” by Takano, Maejima, Yamaguchi and Morishima
Conference:
Type(s):
Title:
- Anime Colorization Using Segment Matching With Candidate Colors
Session/Category Title:
- Images, Video & Computer Vision
Presenter(s)/Author(s):
Abstract:
A novel method for automatic colorization of anime line drawings achieves improved accuracy over state-of-the-art segment matching-based approaches by leveraging semantic segmentation and color shuffling processes without relying on flow estimation, effectively addressing challenges posed by large motion gaps and small regions.
References:
[1] Yuekun Dai, Shangchen Zhou, Qinyue Li, Chongyi Li, and Chen Change Loy. 2024. Learning Inclusion Matching for Animation Paint Bucket Colorization. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 25544–25553.
[2] Akinobu Maejima, Seitaro Shinagawa, Hiroyuki Kubo, Takuya Funatomi, Tatsuo Yotsukura, Satoshi Nakamura, and Yasuhiro Mukaigawa. 2024. Continual few-shot patch-based learning for anime-style colorization. Comp. Visual Media 10, 4 (2024), 705–723.
