MangaNinja: Line Art Colorization with Precise Reference Following
Zhiheng Liu, Ka Leong Cheng, Xi Chen, Jie Xiao, Hao Ouyang, Kai Zhu,, Yu Liu, Yujun Shen, Qifeng Chen, Ping Luo

TL;DR
MangaNinja introduces a diffusion-based method for reference-guided line art colorization, achieving precise character detail transfer and interactive control, surpassing existing solutions in accuracy and versatility.
Contribution
The paper presents novel patch shuffling and point-driven control mechanisms that enhance detail accuracy and user interaction in line art colorization.
Findings
Outperforms current methods in colorization precision
Effective in challenging and cross-character cases
Demonstrates flexible multi-reference harmonization
Abstract
Derived from diffusion models, MangaNinjia 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, cross-character colorization, multi-reference harmonization, beyond the reach of existing algorithms.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · 3D Shape Modeling and Analysis · Handwritten Text Recognition Techniques
MethodsDiffusion
