Fast Sprite Decomposition from Animated Graphics
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 21 of its 35 references that are in the map. First posted on arXiv 7 Aug 2024.
Builds on
21 of 35 references.
References · 21
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
- 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
- 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
- 2017Deep Image Priorcited by 1,098
- 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
- 2023Track Anything: Segment Anything Meets Videoscited by 234
- 2021Layered Neural Atlases for Consistent Video Editingcited by 137
- 2018"Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priorscited by 114
- 2021CanvasVAE: Learning to Generate Vector Graphic Documentscited by 95
9 more
- 2022Towards Layer-wise Image Vectorizationcited by 79
- 2023Learning Neural Volumetric Representations of Dynamic Humans in Minutescited by 70
- 2022Segmenting Moving Objects via an Object-Centric Layered Representationcited by 63
- 2023Shape-aware Text-driven Layered Video Editingcited by 54
- 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
- 2021Omnimatte: Associating Objects and Their Effects in Videocited by 50
- 2021MarioNette: Self-Supervised Sprite Learningcited by 35
- 2021De-rendering Stylized Textscited by 24
- 2018Unsupervised Image Decomposition in Vector Layerscited by 5
Built on by
Citing papers per year: 2025: 2.
2 papers.
- 2025LayerD: Decomposing Raster Graphic Designs into Layerscited by 21
- 2025MG-Gen: Single Image to Motion Graphics Generationcited by 0
- 2025LayerD: Decomposing Raster Graphic Designs into Layers29 Sep 2025
- 2025MG-Gen: Single Image to Motion Graphics Generation3 Apr 2025