AniDoc: Animation Creation Made Easier

TL;DR

AniDoc leverages video diffusion models and correspondence matching to automate coloring and in-betweening in 2D animation, significantly reducing labor costs and simplifying the animation creation process.

Contribution

The paper introduces AniDoc, a novel AI tool that automates coloring and in-betweening in 2D animation using video diffusion models and explicit guidance, improving robustness and ease of use.

Findings

Automates line art colorization with strong robustness to character variations.

Enables automatic in-betweening for temporally consistent animations.

Reduces manual labor in 2D animation production.

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.