APES: Articulated Part Extraction from Sprite Sheets
This addresses the labor-intensive task of partitioning characters into moving parts for artists creating 2D animations, but it is incremental as it builds on existing methods for part extraction.
The paper tackles the problem of automatically identifying articulated parts (e.g., head, torso, limbs) from a small set of character poses in sprite sheets, which are used for creating 2D character animations, and demonstrates significantly better performance than alternatives both qualitatively and quantitatively.
Rigged puppets are one of the most prevalent representations to create 2D character animations. Creating these puppets requires partitioning characters into independently moving parts. In this work, we present a method to automatically identify such articulated parts from a small set of character poses shown in a sprite sheet, which is an illustration of the character that artists often draw before puppet creation. Our method is trained to infer articulated parts, e.g. head, torso and limbs, that can be re-assembled to best reconstruct the given poses. Our results demonstrate significantly better performance than alternatives qualitatively and quantitatively.Our project page https://zhan-xu.github.io/parts/ includes our code and data.