Design and Implementation of Game 3D Character Creation Framework Using Stable Diffusion
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The gaming industry is experiencing rapid growth due to recent advances in technology. Game engines such as Unity and Unreal are being actively utilized. These game engines offer a variety of plugins to naturally extend the functionality of the engine. Among them, innovations in 3D graphics technology have made game characters more expressive and enhanced the user experience. However, traditional 3D modeling approaches can sometimes bring limitations and challenges. In particular there are problems with the representation of fine details when utilizing general photos through AI scanning. This paper aims to overcome these difficulties by designing and implementing a game 3D character generation framework using Stable Diffusion. By improving the creation process by utilizing concept art images without hairstyles, it enables fast and efficient character creation. The application of this framework allows for faster and more consistent character creation with fewer steps in the creation process and helps game developers to adapt characters to the engine more easily and quickly. In addition, we verified the effectiveness and scalability of the 3D game character data generated by Stable Diffusion by checking the animation behavior in the game engine.
Abstract
The gaming industry is experiencing rapid growth due to recent advances in technology. Game engines such as Unity and Unreal are being actively utilized. These game engines offer a variety of plugins to naturally extend the functionality of the engine. Among them, innovations in 3D graphics technology have made game characters more expressive and enhanced the user experience. However, traditional 3D modeling approaches can sometimes bring limitations and challenges. In particular there are problems with the representation of fine details when utilizing general photos through AI scanning. This paper aims to overcome these difficulties by designing and implementing a game 3D character generation framework using Stable Diffusion. By improving the creation process by utilizing concept art images without hairstyles, it enables fast and efficient character creation. The application of this framework allows for faster and more consistent character creation with fewer steps in the creation process and helps game developers to adapt characters to the engine more easily and quickly. In addition, we verified the effectiveness and scalability of the 3D game character data generated by Stable Diffusion by checking the animation behavior in the game engine.
참고문헌 (10)
- 최종인, "앙상블 엔진: 비주얼 노벨 게임 제작을 위한 프레임워크 설계", 한국컴퓨터정보학회논문지, 24(5), pp.11~17 (2019), 한국컴퓨터정보학회[DOI]
- 최정우, "스캔 기반의 게임 캐릭터로 만든 실사형 얼굴 랜드마크 데이터세트", 디지털콘텐츠학회논문지, 23(11), pp.2259~2268 (2022), 한국디지털콘텐츠학회
- Jae-Yong Seo, "Stable Diffusion-based Automatic Game Avatar Generation and Recommendation Method", Proceedings of KIIT Conference, pp.739~742 (2023)
- Rombach, R., "High-resolution image synthesis with latent diffusion models", Proceedings of the IEEE, 2022, 10684~10695
- Jang So Young, "Conditional Music Composition Model Leveraging the Latent Space based on Music VAE", Proceedings of Symposium of the Korean Institute of communications and Information Sciences, pp.410~411 (2023)
- Feng Wang, "Application of Stable Diffusion in Game Character Design and Improvement Strategies", Korean Contents Society's General Academic Conference, pp.99~100 (2023)
- 리징하오, "자동 생성 애니메이션에 효율적인 토폴로지 연구", 만화애니메이션연구, (71), pp.31~52 (2023), 한국만화애니메이션학회
- 백종열, "3D애니메이션제작의 효율성 향상을 위한 오토 리깅 툴의 활용에 대한 연구", 만화애니메이션연구, (49), pp.247~265 (2017), 한국만화애니메이션학회[DOI]
- 전효경, "근로환경 변화에 따른 딥러닝 클라우드 서비스 기술을 활용한 캐릭터 애니메이션 리타겟팅에 관한 연구", 멀티미디어학회논문지, 26(6), pp.753~760 (2023), 한국멀티미디어학회
- 김윤정, "3D 캐릭터 얼굴 모델의 폴리곤 리덕션 연구", 애니메이션연구, 14(3), pp.138~152 (2018), 한국애니메이션학회