从动态图形中快速分解精灵

Fast Sprite Decomposition from Animated Graphics

August 7, 2024

作者: Tomoyuki Suzuki, Kotaro Kikuchi, Kota Yamaguchi

cs.AI

摘要

本文提出了一种将动画图形分解为精灵（sprites）的方法，精灵是一组基本元素或层。我们的方法建立在优化精灵参数以适应光栅视频的基础上。为了提高效率，我们假设精灵的静态纹理，以减少搜索空间，同时利用纹理先验模型来防止伪影。为了进一步加快优化过程，我们引入了利用预训练视频对象分割模型和用户输入的单帧注释初始化精灵参数的方法。为了进行研究，我们从在线设计服务构建了Crello Animation数据集，并定义了用于衡量提取精灵质量的定量指标。实验证明，我们的方法在质量/效率权衡方面明显优于类似分解任务的基准方法。

English

This paper presents an approach to decomposing animated graphics into sprites, a set of basic elements or layers. Our approach builds on the optimization of sprite parameters to fit the raster video. For efficiency, we assume static textures for sprites to reduce the search space while preventing artifacts using a texture prior model. To further speed up the optimization, we introduce the initialization of the sprite parameters utilizing a pre-trained video object segmentation model and user input of single frame annotations. For our study, we construct the Crello Animation dataset from an online design service and define quantitative metrics to measure the quality of the extracted sprites. Experiments show that our method significantly outperforms baselines for similar decomposition tasks in terms of the quality/efficiency tradeoff.