Game effect sprite generation with minimal data via conditional GAN

作者：

Highlights：

• We propose a simple 2D game effect sprite generation technique called a GESGAN.

• GESGAN is capable of generating style-translated images for varied shapes and styles.

• GESGAN can perform 2D image sprite generation tasks in near real-time.

摘要

•We propose a simple 2D game effect sprite generation technique called a GESGAN.•GESGAN is capable of generating style-translated images for varied shapes and styles.•GESGAN can perform 2D image sprite generation tasks in near real-time.

论文关键词：Deep learning,Conditional GAN,Game effect,Game sprite,Generative adversarial networks,Style transfer

论文评审过程：Received 20 October 2021, Revised 1 August 2022, Accepted 7 August 2022, Available online 17 August 2022, Version of Record 1 September 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118491