A Missing Data Imputation GAN for Character Sprite Generation
Universidade Federal de Minas Gerais, Brazil ²Departamento de Computação
Centro Federal de Educação Tecnológica de Minas Gerais, Brazil
![Sample character with a missing pose generated using our proposed model]{There are four examples, each displaying three poses of a character (e.g., facing right, front, left) being used to generate a missing sprite (e.g., facing back). Each example uses the other three directions to produce a different missing pose.](demo/teaser.svg)
Abstract
Creating and updating pixel art character sprites with many frames spanning different animations and poses takes time and can quickly become repetitive. However, that can be partially automated to allow artists to focus on more creative tasks. In this work, we concentrate on creating pixel art character sprites in a target pose from images of them facing other three directions. We present a novel approach to character generation by framing the problem as a missing data imputation task. Our proposed generative adversarial networks model receives the images of a character in all available domains and produces the image of the missing pose. We evaluated our approach in the scenarios with one, two, and three missing images, achieving similar or better results to the state-of-the-art when more images are available. We also evaluate the impact of the proposed changes to the base architecture.
Interactive Demo
