AniDoc: Animation Creation Made Easier
Yihao Meng, Hao Ouyang, Hanlin Wang, Qiuyu Wang, Wen Wang, Ka Leong Cheng, Zhiheng Liu, Yujun Shen, Huamin Qu
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper13
- EasyCreator: Empowering 4D Creation through Video InpaintingYue Ma, Kunyu Feng, Xinhua Zhang, Hongyu Liu 等ICLR 2026 · 被引用 47 次
- ToonComposer: Streamlining Cartoon Production with Generative Post-KeyframingLingen Li, Guangzhi Wang, Zhaoyang Zhang, Yaowei Li 等ICLR 2026 · 被引用 8 次
- EEdit ⚡: Rethinking the Spatial and Temporal Redundancy for Efficient Image EditingZexuan Yan, Yue Ma, Chang Zou, Wenteng Chen 等ICCV 2025 · 被引用 5 次
- A Unified Framework for Industrial Cel-Animation Colorization with Temporal-Structural AwarenessXiaoyi Feng, Tao Huang, Peng Wang, Zizhou Huang 等ICCV 2025 · 被引用 3 次
- LayerAnimate: Layer-Level Control for AnimationYuxue Yang, Lue Fan, Zuzeng Lin, Feng Wang 等ICCV 2025 · 被引用 3 次
它引用的顶会 Paper11
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 被引用 6,759 次
- LightGlue: Local Feature Matching at Light SpeedPhilipp Lindenberger, Paul-Edouard Sarlin, Marc PollefeysICCV 2023 · 被引用 936 次
- SEINE: Short-to-Long Video Diffusion Model for Generative Transition and PredictionXinyuan Chen, Yaohui Wang, Lingjun Zhang, Shaobin Zhuang 等ICLR 2024 · 被引用 226 次
- Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing LossHyunsu Kim, Ho Young Jhoo, Eunhyeok Park, Sungjoo YooICCV 2019 · 被引用 119 次
相关 Paper
- AnimeColor: Reference-based Animation Colorization with Diffusion TransformersYuhong Zhang, Liyao Wang, Han Wang, Danni Wu 等ACM MM 2025 · 被引用 2 次
- Magiccolor: Multi-Instance Sketch ColorizationYinhan Zhang, Yue Ma, Bingyuan Wang, Qifeng Chen 等ICCV 2025 · 被引用 3 次
- Learning Inclusion Matching for Animation Paint Bucket ColorizationYuekun Dai, Shangchen Zhou, Qinyue Li, Chongyi Li 等CVPR 2024
- DACoN: DINO for Anime Paint Bucket Colorization with Any Number of Reference ImagesKazuma Nagata, Naoshi KanekoICCV 2025 · 被引用 1 次
- Cobra: Efficient Line Art COlorization with BRoAder ReferencesJunhao Zhuang, Lingen Li, Xuan Ju, Zhaoyang Zhang 等SIGGRAPH 2025 · 被引用 2 次
