MangaNinja: Line Art Colorization with Precise Reference Following
Abstract
Derived from diffusion models, MangaNinja specializes in the task of reference-guided line art colorization. We incorporate two thoughtful designs to ensure precise character detail transcription, including a patch shuffling module to facilitate correspondence learning between the reference color image and the target line art, and a point-driven control scheme to enable fine-grained color matching. Experiments on a self-collected benchmark demonstrate the superiority of our model over current solutions in terms of precise colorization. We further showcase the potential of the proposed interactive point control in handling challenging cases (*e.g.*, extreme poses and shadows), cross-character colorization, multi-reference harmonization, *etc.*, beyond the reach of existing algorithms.
Cite
Text
Liu et al. "MangaNinja: Line Art Colorization with Precise Reference Following." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.00532Markdown
[Liu et al. "MangaNinja: Line Art Colorization with Precise Reference Following." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/liu2025cvpr-manganinja/) doi:10.1109/CVPR52734.2025.00532BibTeX
@inproceedings{liu2025cvpr-manganinja,
title = {{MangaNinja: Line Art Colorization with Precise Reference Following}},
author = {Liu, Zhiheng and Cheng, Ka Leong and Chen, Xi and Xiao, Jie and Ouyang, Hao and Zhu, Kai and Liu, Yu and Shen, Yujun and Chen, Qifeng and Luo, Ping},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2025},
pages = {5666-5677},
doi = {10.1109/CVPR52734.2025.00532},
url = {https://mlanthology.org/cvpr/2025/liu2025cvpr-manganinja/}
}