APES: Articulated Part Extraction from Sprite Sheets

TL;DR

This paper introduces APES, a method for automatically extracting articulated parts from sprite sheets to facilitate 2D character animation creation, outperforming existing approaches both qualitatively and quantitatively.

Contribution

The novel approach automatically identifies articulated character parts from minimal sprite sheet data, streamlining the puppet creation process for 2D animations.

Findings

Significantly improved performance over existing methods

Effective reconstruction of character poses from extracted parts

Applicable to various sprite sheet styles

Abstract

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.