Generating Gameplay-Relevant Art Assets with Transfer Learning
arXiv:2010.01681
Abstract
In game development, designing compelling visual assets that convey gameplay-relevant features requires time and experience. Recent image generation methods that create high-quality content could reduce development costs, but these approaches do not consider game mechanics. We propose a Convolutional Variational Autoencoder (CVAE) system to modify and generate new game visuals based on their gameplay relevance. We test this approach with Pokémon sprites and Pokémon type information, since types are one of the game's core mechanics and they directly impact the game's visuals. Our experimental results indicate that adopting a transfer learning approach can help to improve visual quality and stability over unseen data.
7 pages, 8 figures
References in corpus (6)
- An Introduction to Variational Autoencoders
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Autoencoding beyond pixels using a learned similarity metric
- Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
- Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
- Texture Synthesis with Recurrent Variational Auto-Encoder