DOI QR코드

DOI QR Code

AI Art Creation Case Study for AI Film & Video Content

AI 영화영상콘텐츠를 위한 AI 예술창작 사례연구

  • 전병원 (동의대학교 영화트랜스미디어연구소)
  • Received : 2021.02.18
  • Accepted : 2021.04.06
  • Published : 2021.05.31

Abstract

Currently, we stand between computers as creative tools and computers as creators. A new genre of movies, which can be called a post-cinema situation, is emerging. This paper aims to diagnose the possibility of the emergence of AI cinema. To confirm the possibility of AI cinema, it was examined through a case study whether the creation of a story, narrative, image, and sound, which are necessary conditions for film creation, is possible by artificial intelligence. First, we checked the visual creation of AI painting algorithms Obvious, GAN, and CAN. Second, AI music has already entered the distribution stage in the market in cooperation with humans. Third, AI can already complete drama scripts, and automatic scenario creation programs using big data are also gaining popularity. That said, we confirmed that the filmmaking requirements could be met with AI algorithms. From the perspective of Manovich's 'AI Genre Convention', web documentaries and desktop documentaries, typical trends post-cinema, can be said to be representative genres that can be expected as AI cinemas. The conditions for AI, web documentaries and desktop documentaries to exist are the same. This article suggests a new path for the media of the 4th Industrial Revolution era through research on AI as a creator of post-cinema.

현재 우리는 창작도구로서 컴퓨터와 창작자로서 컴퓨터 사이에 서 있다. 또한 포스트 시네마적 상황이라 할 수 있는 새로운 장르의 영화들이 등장하고 있다. 본 논문은 AI 시네마의 출현 가능성을 진단하고자 한다. AI 시네마의 가능성을 확인하고자 영화 창작의 필요조건이라 할 수 있는 스토리, 서사의 창작, 이미지의 창작, 사운드의 창작이 인공지능에 의해 가능한지 사례조사를 통해 살펴보았다. 먼저 AI 페인팅 알고리즘인 Obvious, GAN 및 CAN의 시각이미지 생성을 확인했다. 둘째, AI 사운드, 음악은 이미 인간과 협력하여 유통 단계에 들어섰다. 셋째, AI는 이미 드라마 대본을 완성 할 수 있고, 빅 데이터를 활용한 자동 시나리오 제작 프로그램도 인기를 얻고 있다. 즉, 우리는 필수적인 영화 제작 요구 사항이 AI 알고리즘으로 충족될 수 있음을 확인할 수 있다. 마노 비치의 'AI 장르 컨벤션' 관점에서 웹 다큐멘터리와 데스크톱 다큐멘터리는 포스트 시네마로서 AI 시네마의 대표적인 장르라고 할 수 있다. AI, 웹 다큐멘터리, 데스크톱 다큐멘터리가 존재하고 있는 환경이 동일하기 때문이다. 본 논문은 포스트시네마의 창작자로서 AI에 대한 연구를 통해 4차 산업혁명시대 영화라는 매체가 개척해야 할 새로운 길을 제시하고 있다.

Keywords

Acknowledgement

이 논문은 2020년 대한민국 교육부와 한국연구재단의 지원을 받아 수행된 연구임 (NRF-2020S1A5B8102066)

References

  1. L, Manovich, AI Aesthetics, Strelka Press, December 21, 2018.
  2. H. Cohen, On Purpose: An enquiry into possible roles of the computer art, Studio International, 187(962), London: The Studio Trust, pp.11-16, 1974.
  3. C. Menzes, Delving into coding: the art of Harold Cohen, Studio International, London: The Studio Trust, pp.1-14. 2017.
  4. J, Shin, Artificial Intelligence and Big Data in Visual Art, The Korean Journal of Arts Studies. No. 25, pp. 65-89. 2019. https://doi.org/10.20976/KJAS.2019..25.004
  5. J. Condliffe, Some Genius Finally Turned Google's Deep Dream Code into a Web App, Gizmodo, sec. science, p.1. Jun, 2015.
  6. K. Son, Music-Art AI Magenta, Jun, 22, 2017. https://zdnet.co.kr/view/?no=20170622151516 (accessed Jun., 20, 2020).
  7. Homepage of next Rembrandt, https://www.nextrembrandt.com (accessed Jun., 20, 2020).
  8. A, Aarvik, AI creativity and demystification, Academia, 2018
  9. J. Jeong, Originality by artificial intelligence on the open source platform, Gangwon Law, Vol 54, Jun, 2018, pp. 631-640.
  10. B. Ku, Artificial intelligence creates painting and music...Are creativity and art the only human realm?, Hangyeole, Nov. 14. 2016. http://www.hani.co.kr/arti/society/schooling/770226. html (accessed Jun., 20, 2020).
  11. Magenta music sample https://cdn2.vox-cdn.com/uploads/chorus_asset/file/6577761/Google_-_Magenta_music_sample.0.mp3 (accessed Jun., 20, 2020)
  12. B. Ku, Amazon teaches artificial intelligence through music composition, Hangyeole, Dec. 05. 2019. http://www.hani.co.kr/arti/science/future/919756.html (accessed Jun., 20, 2020).
  13. S. Park. The era of artificial intelligence creating art..."Creation is only human property?", Yenhap News. Nov. 01. 2017. https://www.yna.co.kr/view/AKR20171101165000005?input=1195m (accessed Jun., 20, 2020).
  14. CT Insight, AI as a music creation tool, Sep, 2018. http://blog.naver.com/PostView.nhn?blogId=creative_ct&log No=221366842042 (accessed Jun., 20, 2020).
  15. Homepage of enterart https://www.enterarts.net/ (accessed Jun., 20, 2020) enterart music sample https://www.enterarts.net/a-i-m-music (accessed Jun., 20, 2020)
  16. K. Lee. A novel was written by artificial intelligence, can you beat the human heart?, ChosunBiz, Avr, 10, 2018. https://biz.chosun.com/site/data/html_dir/2018/04/09/ 2018040902854.html (accessed Jun., 20, 2020)
  17. S. Jeong. Writing AI, Seoul Economy, Fev. 20, 2019, https://www.sedaily.com/NewsView/1VFDZAJYEO (accessed Jun., 20, 2020).
  18. B. Liu, J. Fu, M. Kato and M, Yoshikawa, Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training, arXiv:1804.08473v4 [cs.CV] Oct. 2018
  19. K. Park. Present and Future of Literature in the Fourth Industrial Revolution, Korean-Chinese Literature Research, Vol 60, Sep, 2018, pp. 1-31.
  20. B, Jeon. The change of cinema-video technology and the response of storytelling in the 4th Industrial Revolution, Humanities Research, .59, 2018. pp. 165-183.
  21. J. Lee. AI "Watson" movie trailer production, Digital Times, Sep,. 02. 2016. http://www.dt.co.kr/contents.html?article_no=2016090202109960813002 (accessed Jun., 20, 2020). Trailer of https://youtu.be/gJEzuYynaiw
  22. https://cloud.google.com/video-intelligence?hl=ko (accessed Jun., 20, 2020).
  23. L. Manovich,. Soft Cinema. 2005 Retrieved August 6, 2018 from Ubu Web: http://www.ubu.com/film/manovich_soft.html
  24. M. Cha & S. Lee, Desktop Documentary & Database Narrative, The Journal of the Convergence on Culture Technology (JCCT), Vol.4, No.3, 2018. https://doi.org/10.17703/JCCT.2018.4.3.75