Skip to yearly menu bar Skip to main content


MarioNette: Self-Supervised Sprite Learning

Dmitriy Smirnov · MICHAEL GHARBI · Matthew Fisher · Vitor Guizilini · Alexei Efros · Justin Solomon

Keywords: [ Deep Learning ] [ Graph Learning ] [ Self-Supervised Learning ]


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.

Chat is not available.