IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

Game Character Image Generation Using GAN

GAN을 이용한 게임 캐릭터 이미지 생성

  • Received : 2023.07.03
  • Accepted : 2023.08.25
  • Published : 2023.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

GAN (Generative Adversarial Networks) creates highly sophisticated counterfeit products by learning real images or text and inferring commonalities. Therefore, it can be useful in fields that require the creation of large-scale images or graphics. In this paper, we implement GAN-based game character creation AI that can dramatically reduce illustration design work costs by providing expansion and automation of game character image creation. This is very efficient in game development as it allows mass production of various character images at low cost.

Keywords

References

  1. A. Radford, L. Metz, C. Soumith, "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks," Computer Science, Machine Learning, arXiv preprint arXiv:1511.06434, 2015.
  2. K. Wang, C. Gou, Y. Duan, Y. Lin, X. Zheng, F. Wang, "Generative Adversarial Networks:Introduction and Outlook," IEEE - CAA Journal of Automatica Sinica, Vol. 4, No. 4, pp. 588-598, 2017. https://doi.org/10.1109/JAS.2017.7510583
  3. M. Cui, M. Kim, S. Choi, S. Lee, "The Usage and Impact of GAN in Graphic Design," Archives of Design Research, Vol. 35, No. 4 pp. 285-307, 2022 (in Korean). https://doi.org/10.15187/adr.2022.11.35.4.285
  4. C. Liao, M. Sawayama, B. Xiao, "A Perceptual Evaluation of the StyleGAN2-ADA Generated Images of Translucent Objects," Journal of Vision, Vol. 22, No. 14, pp. 3642-3642, 2022. https://doi.org/10.1167/jov.22.14.3642
  5. Y. Lu, "Style-based Image Manipulation Using the StyleGAN2-Ada Architecture," Proceedings of 4th International Conference on Computing and Data Science, pp. 29-37, 2022.
  6. R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, "High-Resolution Image Synthesis with Latent Diffusion Models," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684-10695, 2022.
  7. T. Karras, M. Aittala, J. Hellsten, S. Laine, J. Lehtinen, T. Aila, "Training Generative Adversarial Networks with Limited Data," Advances in Neural Information Processing Systems, 33, pp. 12104-12114, 2020.
  8. T. Karras, S. Laine, T. Aila, "A Style-based Generator Architecture for Generative Adversarial Networks," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401-4410, 2019.
  9. H. D. Kim, J. D. Han, H. K. Yang, K. H. Min, "A GAN-based Face Rotation Technique Using 3D Face Model for Game Characters," Journal of Korea Game Society, Vol. 21, No. 3, pp. 13-23, 2021 (in Korean). https://doi.org/10.7583/JKGS.2021.21.3.13
  10. https://pixabay.com/ko
  11. https://charat.me
  12. https://www.freepik.com
  13. https://www.irasutoya.com
  14. https://kr.vonvon.me/quiz/604
  15. J. Kim, M. Jeong, S. Lee, J. Jeong, S. Park, K. Cha "Game Character Image Creation AI," Proceedings of Spring Conference on Korea Multimedia Society, Vol 26, No. 1, pp. 24-27, 2023 (in Korean).
  16. https://github.com/NVlabs/stylegan2-ada-pytorch
  17. D. A. Talib, A. A. Abed, "Real-Time Deepfake Image Generation Based on Stylegan2-ADA," Revue d'Intelligence Artificielle, Vol. 37, No. 2, pp. 397-405, 2023. https://doi.org/10.18280/ria.370216
  18. https://github.com/AUTOMATIC1111/stable-diffusion-webui
  19. https://huggingface.co
  20. https://kmong.com/
  21. S. K. Oh, J. Y. Kang, "A Study on Webtoon Background Image Generation Using CartoonGAN Algorithm," Korea BigData Society, Vol. 7, No. 1, pp. 173-185, 2022.
  22. S. Hicsonmeza, N. Samet, E. Akbas, P. Duygulu, "Ganilla: Generative Adversarial Networks for Image to Illustration Translation," Image and Vision Computing, Elsevier, Vol. 95, 103886, 2020.