2021/04/29 by Dmitriy Smirnov, Michaël Gharbi, Michael Gharbi +10 · 1 voice · 1 citation
Computer Science · #Advanced Vision and Imaging #Animation #Artificial intelligence #Computer Graphics and Visualization Techniques #Computer graphics (images) #Computer science #Construct (python library) #Deep learning #Generative Adversarial Networks and Image Synthesis #Multimedia #Representation (politics) #Sprite (computer graphics) #cs.CV
paper · pdf · doi:10.48550/arxiv.2104.14553
published in arXiv (Cornell University) 34 (Cornell University) · Accepted to NeurIPS 2021
openalex publication_date 2021/04/29 · arxiv created 2021/10/20 · arxiv updated 2021/10/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Artists and video game designers often construct 2D animations using libraries of sprites -- textured patches of objects and characters. We propose a deep learning approach that decomposes sprite-based video animations into a disentangled representation of recurring graphic elements in a self-supervised manner. By jointly learning a dictionary of possibly transparent patches and training a network that places them onto a canvas, we deconstruct sprite-based content into a sparse, consistent, and explicit representation that can be easily used in downstream tasks, like editing or analysis. Our framework offers a promising approach for discovering recurring visual patterns in image collections without supervision.