AniDoc: Animation Creation Made Easier
Yihao Meng, Hao Ouyang, Hanlin Wang, Qiuyu Wang, Wen Wang, Ka Leong Cheng, Zhiheng Liu, Yujun Shen, Huamin Qu
Abstract
The production of 2D animation follows an industry-standard workflow, encompassing four essential stages: character design, keyframe animation, in-betweening, and coloring. Our research focuses on reducing the labor costs in the above process by harnessing the potential of increasingly powerful generative AI. Using video diffusion models as the foundation, AniDoc1emerges as a video line art colorization tool, which automatically converts sketch sequences into colored animations following the reference character specification. Our model exploits correspondence matching as an explicit guidance, yielding strong robustness to the variations (e.g., posture) between the reference character and each line art frame. In addition, our model could even automate the in-betweening process, such that users can easily create a temporally consistent animation by simply providing a character image as well as the start and end sketches. Our code is available at: https://yihaomeng.github.io/AniDocdemo.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 749db294-8a36-4302-8bb0-4a22c4257825Cited by top-tier papers13
- EasyCreator: Empowering 4D Creation through Video InpaintingYue Ma, Kunyu Feng, Xinhua Zhang, Hongyu Liu et al.ICLR 2026 · 47 citations
- ToonComposer: Streamlining Cartoon Production with Generative Post-KeyframingLingen Li, Guangzhi Wang, Zhaoyang Zhang, Yaowei Li et al.ICLR 2026 · 8 citations
- EEdit ⚡: Rethinking the Spatial and Temporal Redundancy for Efficient Image EditingZexuan Yan, Yue Ma, Chang Zou, Wenteng Chen et al.ICCV 2025 · 5 citations
- A Unified Framework for Industrial Cel-Animation Colorization with Temporal-Structural AwarenessXiaoyi Feng, Tao Huang, Peng Wang, Zizhou Huang et al.ICCV 2025 · 3 citations
- LayerAnimate: Layer-Level Control for AnimationYuxue Yang, Lue Fan, Zuzeng Lin, Feng Wang et al.ICCV 2025 · 3 citations
Builds on11
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
- LightGlue: Local Feature Matching at Light SpeedPhilipp Lindenberger, Paul-Edouard Sarlin, Marc PollefeysICCV 2023 · 936 citations
- SEINE: Short-to-Long Video Diffusion Model for Generative Transition and PredictionXinyuan Chen, Yaohui Wang, Lingjun Zhang, Shaobin Zhuang et al.ICLR 2024 · 226 citations
- Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing LossHyunsu Kim, Ho Young Jhoo, Eunhyeok Park, Sungjoo YooICCV 2019 · 119 citations
Related papers
- AnimeColor: Reference-based Animation Colorization with Diffusion TransformersYuhong Zhang, Liyao Wang, Han Wang, Danni Wu et al.ACM MM 2025 · 2 citations
- Magiccolor: Multi-Instance Sketch ColorizationYinhan Zhang, Yue Ma, Bingyuan Wang, Qifeng Chen et al.ICCV 2025 · 3 citations
- Learning Inclusion Matching for Animation Paint Bucket ColorizationYuekun Dai, Shangchen Zhou, Qinyue Li, Chongyi Li et al.CVPR 2024
- DACoN: DINO for Anime Paint Bucket Colorization with Any Number of Reference ImagesKazuma Nagata, Naoshi KanekoICCV 2025 · 1 citation
- Cobra: Efficient Line Art COlorization with BRoAder ReferencesJunhao Zhuang, Lingen Li, Xuan Ju, Zhaoyang Zhang et al.SIGGRAPH 2025 · 2 citations
