CVGRAug 7, 2024

Fast Sprite Decomposition from Animated Graphics

arXiv:2408.03923v13 citationsh-index: 10
Originality Incremental advance
AI Analysis

This work addresses sprite decomposition for animation design, offering incremental improvements in efficiency and quality for domain-specific applications.

The paper tackles the problem of decomposing animated graphics into sprites by optimizing sprite parameters to fit raster video, using static textures and a texture prior model to reduce artifacts. Experiments on the Crello Animation dataset show the method significantly outperforms baselines in quality/efficiency tradeoff.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes