Bridging the Gap: Sketch-Aware Interpolation Network for High-Quality Animation Sketch Inbetweening

TL;DR

This paper introduces SAIN, a deep learning model that improves sketch inbetweening for animation by using multi-level guidance and a multi-stream U-Transformer, supported by a new large-scale dataset.

Contribution

The paper presents a novel sketch-aware interpolation network with multi-level guidance and a multi-stream U-Transformer, and introduces the STD-12K dataset for animation sketch inbetweening.

Findings

SAIN outperforms existing methods on the STD-12K dataset.

The multi-level guidance improves correspondence accuracy.

The dataset enables future research in sketch inbetweening.

Abstract

Hand-drawn 2D animation workflow is typically initiated with the creation of sketch keyframes. Subsequent manual inbetweens are crafted for smoothness, which is a labor-intensive process and the prospect of automatic animation sketch interpolation has become highly appealing. Yet, common frame interpolation methods are generally hindered by two key issues: 1) limited texture and colour details in sketches, and 2) exaggerated alterations between two sketch keyframes. To overcome these issues, we propose a novel deep learning method - Sketch-Aware Interpolation Network (SAIN). This approach incorporates multi-level guidance that formulates region-level correspondence, stroke-level correspondence and pixel-level dynamics. A multi-stream U-Transformer is then devised to characterize sketch inbetweening patterns using these multi-level guides through the integration of self / cross-attention mechanisms. Additionally, to facilitate future research on animation sketch inbetweening, we constructed a large-scale dataset - STD-12K, comprising 30 sketch animation series in diverse artistic styles. Comprehensive experiments on this dataset convincingly show that our proposed SAIN surpasses the state-of-the-art interpolation methods.