AniDoc: Animation Creation Made Easier
Yihao Meng, Hao Ouyang, Hanlin Wang, Qiuyu Wang, Wen Wang, Ka Leong Cheng, Zhiheng Liu, Yujun Shen, Huamin Qu
2024-12-19
Summary
This paper talks about AniDoc, a new tool that simplifies the process of creating 2D animations by using AI to automatically color sketches and fill in missing frames.
What's the problem?
Creating 2D animations is a complicated and time-consuming process that involves several steps: designing characters, creating keyframes (the main poses), drawing in-between frames, and coloring everything. This can be labor-intensive and costly, especially for smaller studios or independent creators who may not have the resources to manage all these tasks effectively.
What's the solution?
AniDoc addresses these challenges by using advanced AI techniques to automate parts of the animation process. It can take a sequence of sketches and automatically color them based on a reference character design. Additionally, AniDoc can fill in the gaps between keyframes (the in-betweening process) by generating the missing frames, allowing for smoother animations. This means users only need to provide a character image and the starting and ending sketches to create a complete animation.
Why it matters?
This research is important because it makes animation creation more accessible and efficient. By reducing the time and effort required to produce high-quality animations, AniDoc empowers artists and smaller studios to focus on creativity rather than tedious tasks. This could lead to more innovative storytelling and artistic expression in the animation industry, making it easier for anyone to create engaging animated content.
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, AniDoc emerges 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://yihao-meng.github.io/AniDoc_demo.