Game Sprite Generator Using a Multi Discriminator GAN
- Authors
- Hong, Seungjin; Kim, Sookyun; Kang, Shinjin
- Issue Date
- 31-Aug-2019
- Publisher
- KSII-KOR SOC INTERNET INFORMATION
- Keywords
- Generative Adversarial Nets (GANs); 2D Game Sprite; Deep Learning; Game Development; Neural Network
- Citation
- KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, v.13, no.8, pp.4255 - 4269
- Journal Title
- KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS
- Volume
- 13
- Number
- 8
- Start Page
- 4255
- End Page
- 4269
- URI
- https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/1173
- DOI
- 10.3837/tiis.2019.08.025
- ISSN
- 1976-7277
- Abstract
- This paper proposes an image generation method using a Multi Discriminator Generative Adversarial Net (MDGAN) as a next generation 2D game sprite creation technique. The proposed GAN is an Autoencoder-based model that receives three areas of information-color, shape, and animation, and combines them into new images. This model consists of two encoders that extract color and shape from each image, and a decoder that takes all the values of each encoder and generates an animated image. We also suggest an image processing technique during the learning process to remove the noise of the generated images. The resulting images show that 2D sprites in games can be generated by independently learning the three image attributes of shape, color, and animation. The proposed system can increase the productivity of massive 2D image modification work during the game development process. The experimental results demonstrate that our MDGAN can be used for 2D image sprite generation and modification work with little manual cost.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - School of Games > Game Software Major > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.