Journal of the Institute of Convergence Signal Processing (융합신호처리학회논문지)

The Korea Institute of Convergence Signal Processing (한국융합신호처리학회)
권호 표지
DOI QR코드

DOI QR Code

Real2Animation: A Study on the application of deepfake technology to support animation production

Real2Animation:애니메이션 제작지원을 위한 딥페이크 기술 활용 연구

  • Dongju Shin (Department of Software, Dongseo University) ;
  • Bongjun Choi (College of Software Convergence, Dongseo University)
  • 신동주 (동서대학교 소프트웨어학과,) ;
  • 최봉준 (동서대학교 소프트웨어융합대학)
  • Received : 2022.09.13
  • Accepted : 2022.09.30
  • Published : 2022.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, various computing technologies such as artificial intelligence, big data, and IoT are developing. In particular, artificial intelligence-based deepfake technology is being used in various fields such as the content and medical industry. Deepfake technology is a combination of deep learning and fake, and is a technology that synthesizes a person's face or body through deep learning, which is a core technology of AI, to imitate accents and voices. This paper uses deepfake technology to study the creation of virtual characters through the synthesis of animation models and real person photos. Through this, it is possible to minimize various cost losses occurring in the animation production process and support writers' work. In addition, as deepfake open source spreads on the Internet, many problems emerge, and crimes that abuse deepfake technology are prevalent. Through this study, we propose a new perspective on this technology by applying the deepfake technology to children's material rather than adult material.

최근 인공지능, 빅데이터, IoT 등의 다양한 컴퓨팅 기술이 발달하고 있다. 특히 콘텐츠 및 의료 산업 등 여러 분야에서 인공지능 기반의 딥페이크(Deepfake) 기술이 다양하게 활용되고 있다. 딥페이크 기술이란 딥러닝과 fake의 합성어로, AI의 핵심기술인 딥러닝을 통해 사람의 얼굴이나 신체를 합성하여 억양, 목소리 등을 따라 하게 만드는 기술이다. 본 논문은 딥페이크 기술을 활용하여 애니메이션 모델과 실제 인물사진의 합성을 통한 가상 캐릭터생성을 연구한다. 이를 통해 애니메이션 제작과정에서 일어나는 여러 가지 비용 손실을 최소화하고 작가들의 작업을 지원할 수 있다. 또한, 딥페이크 오픈소스가 인터넷에 퍼짐에 따라 많은 문제들이 나타나면서 딥페이크 기술을 악용한 범죄가 성행하고 있다. 본 연구를 통해서 딥페이크 기술을 성인물이 아닌 아동물에 적용하여 이 기술에 대한 새로운 관점을 제시한다.

Keywords

Acknowledgement

본 연구는 2022년 학기술정보통신부 및 정보통신기획평가원의 SW중심대학사업 연구결과로 수행되었음(2019-0-01817).

References

  1. M. S. Choi and B. J. Choi, "A Study on the PBL-based AI Education for Computational Thinking", KICSP, Vol. 22, No. 3, 2021, pp 110-115.
  2. S. W. Lee, S. M. Lee, H. M. Joo and Y. J. Nam,"Examining Factors Influencing Early Paid Over-The-Top Video Streaming Market Growth: A Cross-Country Empirical Study", Sustainability, 13(10), 5702, 2021.
  3. "The sound of my heart, Ae-bong and Jo-seok. GFRIEND's motif character eyes", MBN's daily broadcast, 2014.07. Available: https://star.mbn.co.kr/view.php?no=995789&year=2014
  4. B. R. Yi."A Study on Kiduit Character Consuming Trend's Creation process and Characteristics : A Focus on Webtoon The Sound of Mind", The Korean Journal of animation, Vol 12, No. 3, 2016
  5. T. H. Cho, J. P. Jeong and S. M. Choi, "3D Emotional Avatar Creation and Animation using Facial Expression Recognition", JKMS, Vol. 17. No. 9, 2014, pp.1076-1083.
  6. J. H. Kim, J. J. Ahn, B. S. Yang, J. U. Jung And S. S. Woo, "Investigation of the Latest Technology Trends in Data-Based Deepfake Detection Techniques", Journal of the Society for Information Protection, Vol. 30, No. 5, pp.11212, 2020. 10.
  7. J. Park and Y. H. Cho, "Technology Trends Related to Deepfake Video Detection",2019 Korea Software Conference Paper Collection, 724-726
  8. I. Korshunova, W. Shi, J. Dambre and L. Theis. "Fast face-swap using convolutional neural networks." Proceedings of the IEEE international conference on computer vision. 2017.