DOI QR코드

DOI QR Code

디지털 에셋 창작을 위한 생성형 AI 기술 동향 및 발전 전망

Generative AI Technology Trends and Development Prospects for Digital Asset Creation

  • 이기석 (XR콘텐츠연구실 ) ;
  • 이승욱 (공간콘텐츠연구실 ) ;
  • 윤민성 (XR콘텐츠연구실 ) ;
  • 유정재 (지능형콘텐츠인식연구실) ;
  • 오아름 (콘텐츠융합연구실 ) ;
  • 최인문 (감성디지털휴먼연구실) ;
  • 김대욱 (실감상호작용연구실 )
  • K.S. Lee ;
  • S.W. Lee ;
  • M.S. Yoon ;
  • J.J. Yu ;
  • A.R. Oh ;
  • I.M. Choi ;
  • D.W. Kim
  • 발행 : 2024.04.01

초록

With the recent rapid development of artificial intelligence (AI) technology, its use is gradually expanding to include creative areas and building new content using generative AI solutions, reaching beyond existing data analysis and reasoning applications. Content creation using generative AI faces challenges owing to technical limitations and other aspects such as copyright compliance. Nevertheless, generative AI may increase the productivity of experts and overcome barriers to creative work by allowing users to easily express their ideas as digital content. Thus, various types of applications will continue to emerge. As images and videos can be created using text input on a prompt, generative AI allows to create and edit digital assets quickly. We present trends in generative AI technology for images, videos, three-dimensional (3D) assets and scenes, digital humans, interactive content, and interfaces. In addition, the prospects for future technological development in this field are discussed.

키워드

과제정보

본 연구는 과학기술정보통신부의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임[No. RS-2023-00225441, 디지털 에셋의 다형성 변형을 위한 지식, 정보 구조화 기술].

참고문헌

  1. R. Rombach et al., "High-resolution image synthesis with latent diffusion models," in Proc. IEEE/CVF CVPR, (New Orleans, LA, USA), June 2022, pp. 10684-10695. 
  2. A. Blattmann et al., "Align your latents: High-resolution video synthesis with latent diffusion models," in Proc. IEEE/CVF CVPR, (Vancouver, Canada), June 2023, pp. 22563-22575. 
  3. GANverse3D: A neural network from NVIDIA reconstructs a 3D Model from a single photo, 2022, https://neurohive.io/en/news/ganverse3d-a-neuralnetwork-from-nvidia-reconstructs-a-3d-model-from-a-single-photo/ 
  4. G.B.M. Stan et al., "LDM3D: Latent diffusion model for 3D," arXiv preprint, CoRR, 2023, arXiv: 2305.10853. 
  5. A. Vaswani et al., "Attention is all you need," in Proc. NIPS, (Long Beach, CA, USA), Dec. 2017, pp. 5998-6008. 
  6. B. Jiang et al., "MotionGPT: Human motion as a foreign language," arXiv preprint, CoRR, 2023, arXiv: 2306.14795. 
  7. J.S. Park et al., "Generative agents: Interactive simulacra of human behavior," in Proc. ACM UIST, (San Francisco, CA, USA), Oct. 2023, pp. 1-22. 
  8. AI Dungeon, https://play.aidungeon.com/(Retrieved Date Accessed 2024. 1. 1.) 
  9. 미라클아이, ""잘 지내?" "그렇게 좋진 않아"...같은 게임 샀는데 내용 다르다고?," 2024. 1. 1. 
  10. Bitmagic Games, https://bitmagic.games/(Retrieved Date Accessed 2024. 1. 2.) 
  11. A. Summerville and M. Mateas, "Super mario as a string: Platformer level generation via lstms," arXiv preprint, CoRR, 2016, arXiv: 1603.00930. 
  12. V. Volz et al., "Evolving mario levels in the latent space of a deep convolutional generative adversarial network," in Proc. GECCO, (Kyoto, Japan), Jul. 2018, pp. 221-228. 
  13. A. Sarkar, Z. Yang, and S. Cooper, "Conditional level generation and game blending," arXiv preprint, CoRR, 2020, arXiv: 2010.07735. 
  14. A. Khalifa et al., "Pcgrl: Procedural content generation via reinforcement learning," AAAI Conf. Art. Intell. Interact. Digit. Entertain., vol. 16, no. 1, 2020, pp. 95-101. 
  15. S. Earle et al., "Learning controllable content generators," in Proc. IEEE CoG, (Copenhagen, Denmark), Aug. 2021, pp. 1-9. 
  16. Z. Jiang et al., "Learning controllable 3D level generators," in Proc. FDG, (Athens, Greece), Sept. 2022, pp. 1-9. 
  17. R. Martin-Brualla et al., "Nerf in the wild: Neural radiance fields for unconstrained photo collections," in Proc. IEEE/CVF CVPR, (Virtual), June 2021. 
  18. F. Liu, M. Zhang, and R. Budiu, AI as a UX Assistant, Oct. 2023, https://www.nngroup.com/articles/ai-roles-ux/#Design_Recommendations