Deep Geometrized Cartoon Line Inbetweening

TL;DR

This paper introduces AnimeInbet, a novel graph-based approach for automatic inbetweening of line drawings in animation, effectively capturing line details and outperforming existing methods especially with large motions.

Contribution

The paper proposes a new geometrization-based method, AnimeInbet, with novel modules and a new dataset, addressing the limitations of raster image interpolation for line drawings.

Findings

AnimeInbet produces high-quality intermediate frames.

Outperforms existing methods quantitatively and qualitatively.

Effective in cases with large motions.

Abstract

We aim to address a significant but understudied problem in the anime industry, namely the inbetweening of cartoon line drawings. Inbetweening involves generating intermediate frames between two black-and-white line drawings and is a time-consuming and expensive process that can benefit from automation. However, existing frame interpolation methods that rely on matching and warping whole raster images are unsuitable for line inbetweening and often produce blurring artifacts that damage the intricate line structures. To preserve the precision and detail of the line drawings, we propose a new approach, AnimeInbet, which geometrizes raster line drawings into graphs of endpoints and reframes the inbetweening task as a graph fusion problem with vertex repositioning. Our method can effectively capture the sparsity and unique structure of line drawings while preserving the details during inbetweening. This is made possible via our novel modules, i.e., vertex geometric embedding, a vertex correspondence Transformer, an effective mechanism for vertex repositioning and a visibility predictor. To train our method, we introduce MixamoLine240, a new dataset of line drawings with ground truth vectorization and matching labels. Our experiments demonstrate that AnimeInbet synthesizes high-quality, clean, and complete intermediate line drawings, outperforming existing methods quantitatively and qualitatively, especially in cases with large motions. Data and code are available at https://github.com/lisiyao21/AnimeInbet.