GAN을 이용한 게임 캐릭터 이미지 생성
Game Character Image Generation Using GAN
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
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.
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.
참고문헌 (22)
- A. Radford, "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks", Computer Science, Machine Learning, ~ (2015)
- K. Wang, "Generative Adversarial Networks:Introduction and Outlook", IEEE-CAA Journal of Automatica Sinica, 4(4), pp.588~598 (2017)
- CUI MINGZHU, "그래픽 디자인 분야에서 GAN의 활용 방안 및 영향 연구", 디자인학연구, 35(4), pp.285~307 (2022), 한국디자인학회[DOI]
- C. Liao, "A Perceptual Evaluation of the StyleGAN2-ADA Generated Images of Translucent Objects", Journal of Vision, 22(14), pp.3642~3642 (2022)
- 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)
- R. Rombach, "High-Resolution Image Synthesis with Latent Diffusion Models", Proceedings of the IEEE, 2022, 10684~10695
- T. Karras, "Training Generative Adversarial Networks with Limited Data", Advances in Neural Information Processing Systems, 33, pp.12104~12114 (2020)
- T. Karras, "A Style-based Generator Architecture for Generative Adversarial Networks", Proceedings of the IEEE, 2019, 4401~4410
- 김한동, "3D 얼굴 모델 기반의 GAN을 이용한 게임 캐릭터 회전 기법", 한국게임학회 논문지, 21(3), pp.13~24 (2021), 한국게임학회
- J. Kim, "Game Character Image Creation AI", Proceedings of Spring Conference on Korea Multimedia Society, 26(1), pp.24~27 (2023)
- D. A. Talib, "Real-Time Deepfake Image Generation Based on Stylegan2-ADA", Revue d'Intelligence Artificielle, 37(2), pp.397~405 (2023)
- 오세규, "CartoonGAN 알고리즘을 이용한 웹툰(Webtoon) 배경 이미지 생성에 관한 연구", 한국빅데이터학회 학회지, 7(1), pp.173~185 (2022), 사)한국빅데이터학회[DOI]
- S. Hicsonmeza, "Ganilla: Generative Adversarial Networks for Image to Illustration Translation", Image and Vision Computing, Elsevier, 95, pp.103886~ (2020)