從動畫圖形中快速進行精靈分解

Fast Sprite Decomposition from Animated Graphics

August 7, 2024

作者: Tomoyuki Suzuki, Kotaro Kikuchi, Kota Yamaguchi

cs.AI

摘要

本文提出了一種將動畫圖形分解為精靈（sprites）的方法，這些精靈是基本元素或層。我們的方法建立在優化精靈參數以配合光柵視頻的基礎上。為了提高效率，我們假設精靈使用靜態紋理，以減少搜索空間，同時使用紋理先驗模型來防止產生瑕疵。為了進一步加快優化過程，我們引入了使用預先訓練的視頻物體分割模型和用戶輸入的單幀標註來初始化精靈參數。在我們的研究中，我們從在線設計服務中構建了Crello Animation數據集，並定義了量化指標來衡量提取的精靈的質量。實驗表明，我們的方法在質量/效率平衡方面顯著優於類似分解任務的基準方法。

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.