论文标题
通过转移学习生成与游戏玩法相关的艺术资产
Generating Gameplay-Relevant Art Assets with Transfer Learning
论文作者
论文摘要
在游戏开发中，设计引人入胜的视觉资产传达与游戏玩法相关的功能需要时间和经验。创建高质量内容的最新图像生成方法可以降低开发成本，但是这些方法不考虑游戏机制。我们提出了一个卷积变量自动编码器（CVAE）系统，以根据其游戏玩法的相关性修改和生成新的游戏视觉效果。我们使用PokémonSprites和Pokémon类型信息测试这种方法，因为类型是游戏的核心机制之一，它们直接影响了游戏的视觉效果。我们的实验结果表明，采用转移学习方法可以帮助提高视觉质量和稳定性，而不是看不见的数据。
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.
