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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Shen, Jiaming, Hu, Kun, Bao, Wei, Chen, Chang Wen, Wang, Zhiyong
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911987755122688
author Shen, Jiaming
Hu, Kun
Bao, Wei
Chen, Chang Wen
Wang, Zhiyong
author_facet Shen, Jiaming
Hu, Kun
Bao, Wei
Chen, Chang Wen
Wang, Zhiyong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_13273
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Bridging the Gap: Sketch-Aware Interpolation Network for High-Quality Animation Sketch Inbetweening
Shen, Jiaming
Hu, Kun
Bao, Wei
Chen, Chang Wen
Wang, Zhiyong
Computer Vision and Pattern Recognition
Multimedia
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.
title Bridging the Gap: Sketch-Aware Interpolation Network for High-Quality Animation Sketch Inbetweening
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2308.13273