All Issue

2026 Vol.14, Issue 1 Preview Page

Research Article

31 March 2026. pp. 11-21
Abstract
본 연구는 대한민국의 역사 교육에서 반복적으로 다루어지는 주요 위인들의 단색 또는 저해상도의 이미지를 AI를 활용한 해상도 복원 (Super–Resolution) 및 색채 복원(Colorization) 기술을 통해 생생하게 재현 하는데 목표를 삼고 있다. 나아가 2D 이미지를 바탕으로 3D 복원 및 이를 다중 시점 이미지로 변환한 뒤 디지털 홀로그램으로 구현하고자 한다. 이는 미래 역사 교육, 교육 콘텐츠 개발뿐만 아니라 디지털 문화유산 보존이라는 측면에서도 연구적, 사회적 의미를 지닌다. 실험은 대한민국 초·중·고 역사 교육에서 중요하게 다뤄지는 9인 위인의 흑백 및 저해상도의 이미지로 AI를 이용한 색복원 및 해상도를 업그레이드 하고 이후 깊이 추정 및 다시점 이미지 합성, 홀로그램 인코딩의 전과정을 수행한다.
This study aims to vividly reproduce the monochrome or low-resolution images of major great figures repeatedly covered in Korean history education through artificial intelligence-based high-resolution restoration and colorization technology. Furthermore, it is intended to be implemented as a digital hologram through 3D restoration and multi-view image extraction from 2D images. This technological approach has academic and social value not only in the development of future historical education contents but also in the preservation of digital cultural heritage.The experiment utilizes black-and-white and low-resolution images of 9 great figures in elementary, middle, and high school history education in Korea, and then the entire process of depth estimation, multi-view image synthesis, and hologram encoding is performed.
References
  1. B. Javidi, and F. Okano, “Three Dimensional Television, Video, and Display Technologies”, Springer, 2011.

  2. D. Gabor, “A new microscopic principle”, Nature, Vol. 161, pp. 777-778, 1948.

    10.1038/161777a0
  3. Y. N. Denisyuk, “On the reproduction of the optical properties of an object by the wave field of its scattered radiation”, Opt. Spectrosc., Vol. 14, pp. 279-284, 1963.

  4. E. N. Leith, and J. Upatnieks, “Wavefront Reconstruction with Continuous-Tone Objects”, J. Opt. Soc. Am., Vol. 53, pp. 1377-1381, 1963.

    10.1364/JOSA.53.001377
  5. A. Yolalmaz, et al., “Comprehensive Deep Learning Model for Optical Holography (DOENet)”, arXiv:2105.13060, https://arxiv.org/abs/2105.13060.

  6. Y. Chen, Z. Li, Q. Fu, and L. Waller, “Fourier Imager Network (FIN): A Deep Neural Network for Hologram Reconstruction”, arXiv:2204.10533, https://arxiv.org/abs/2204.10533.

  7. Y. Go, S. Lee, S. Park, and D. Kim, “Deep Learning-Based Hologram Generation Using a White-Light Source”, Scientific Reports, Vol. 10, No. 8579, May 2020.

    10.1038/s41598-020-65716-4 32488035 PMC7265409
  8. A. Sarakinos, et al., “Direct-write digital holographic printing of color reflection holograms for visualization of artworks and historic sites”, 11th Int. Symposium on Display Holography, June 2018.

  9. S. Zacharovas, “Advances in Digital Holography”, IWHM 2008 International Workshop on Holographic Memories Digests, pp. 55-67, November 2008.

  10. X. Wang, et al., “ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks”, European Conference on Computer Vision (ECCV), pp. 63-79, 2018.

    10.1007/978-3-030-11021-5_5
  11. Y. Feng, et al., “Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network”, European Conference on Computer Vision (ECCV), pp. 534-551, 2018.

    10.1007/978-3-030-01264-9_33
  12. E. Dashdavaa, et al., “Holographic stereogram printing based on digitally computed content generation platform”, Proc. SPIE, Vol. 10944, 109440M, February 2019.

    10.1117/12.2510902
Information
  • Publisher :The Society of Convergence Knowledge
  • Publisher(Ko) :융복합지식학회
  • Journal Title :The Society of Convergence Knowledge Transactions
  • Journal Title(Ko) :융복합지식학회논문지
  • Volume : 14
  • No :1
  • Pages :11-21