A Missing Data Imputation GAN for Character Sprite Generation
This addresses the repetitive task of creating pixel art animations for artists, though it appears incremental as it builds on existing GAN architectures.
The paper tackles the problem of generating pixel art character sprites in missing poses by framing it as a missing data imputation task, achieving similar or better results than state-of-the-art methods when more input images are available.
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.