방송공학회논문지 (Journal of Broadcast Engineering)

  • 제28권1호
  • /
  • Pages.42-54
  • /
  • 2023
  • /
  • 1226-7953(pISSN)
  • /
  • 2287-9137(eISSN)
한국방송∙미디어공학회 (The Korean Institute of Broadcast and Media Engineers)
권호 표지
DOI QR코드

DOI QR Code

신경망 기반 블록 단위 위상 홀로그램 이미지 압축

Block-based Learned Image Compression for Phase Holograms

  • 최승미 (경희대학교 컴퓨터공학부) ;
  • 박수용 (경희대학교 컴퓨터공학부) ;
  • 반현민 (경희대학교 컴퓨터공학부) ;
  • 차준영 (경희대학교 소프트웨어융합학과) ;
  • 김휘용 (경희대학교 컴퓨터공학부)
  • 투고 : 2022.11.15
  • 심사 : 2023.01.19
  • 발행 : 2023.01.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

방대한 홀로그램 데이터를 디지털 형식으로 압축하는 것은 중요한 문제이다. 특히, 상용화를 위해 위상 전용 홀로그램의 압축에 관한 연구가 주목된다. 자연 영상에 최적화된 기존 표준 압축 기술은 위상 신호를 압축하는데 적합하지 않으며, 위상 신호에 대해 최적화 가능한 신경망 기반 압축 기술은 좋은 성능을 기대할 수 있으나 고해상도 홀로그램 데이터를 학습하는 데 메모리 문제가 존재한다. 본 논문에서는 메모리 문제를 해결할 수 있는 학습 가능한 신경망 기반의 블록 단위 압축 기술을 위상 전용 홀로그램에 적용해봄으로써 블록 기반이라는 동일 조건 내에서도 제안 방식이 표준 코덱보다 상당한 성능향상을 보일 수 있음을 밝혔다. 신경망 기반의 블록 단위 압축은 기존 코덱과의 호환성을 제공할 수 있으며, 메모리 문제를 해결하는 동시에 위상 전용 홀로그램 압축에 대해 월등히 좋은 성능을 보일 수 있다.

It is an important issue to compress huge holographic data in a digital format. In particular, research on the compression of phase-only holograms for commercialization is noteworthy. Conventional video coding standards optimized for natural images are not suitable for compressing phase signals, and neural network-based compression model that can be optimized for phase signals can achieve high performance, but has a memory issue in learning high-resolution holographic data. In this paper, we show that by applying a block-based learned image compression model that can solve memory problems to phase-only holograms, the proposed method can demonstrate significant performance improvement over standard codecs even under the same conditions as block-based. Block-based learned compression model can provide compatibility with conventional standard codecs, solve memory problems, and can perform significantly better against phase-only hologram compression.

키워드

과제정보

이 논문은 삼성전자미래기술육성센터의 지원을 받아 수행된 연구임 (과제번호 SRFC-IT2202-03).

참고문헌

  1. Oh, K. J., and J. Park. "Research and Standardization Trends of Digital Hologram Compression," Electronics and telecommunications trends, Vol.34, No.6, pp.145-155, Dec 2019. doi: https://doi.org/10.22648/ETRI.2019.J.340613
  2. Ko, Hyunsuk, and Hui Yong Kim. "Deep learning-based compression for phase-only hologram," IEEE Access, Vol.9, pp.79735-79751, May 2021. doi: https://doi.org/10.1109/ACCESS.2021.3084800
  3. Schelkens, Peter, et al. "JPEG Pleno: Providing representation interoperability for holographic applications and devices," ETRI Journal, Vol.41, No.1, pp.93-108, Feb 2019. doi: https://doi.org/10.4218/etrij.2018-0509
  4. Darakis, Emmanouil, and John J. Soraghan. "Compression of interference patterns with application to phase-shifting digital holography," Applied optics, Vol.45, No.11, pp.2437-2443, 2006. doi: https://doi.org/10.1364/AO.45.002437
  5. Blinder, David, et al. "JPEG 2000-based compression of fringe patterns for digital holographic microscopy," Optical Engineering, Vol.53 No.12, pp.123102-123102, Dec 2014. doi: https://doi.org/10.1117/1.OE.53.12.123102
  6. Darakis, Emmanouil, et al. "Visually lossless compression of digital hologram sequences," Image Quality and System Performance VII, SPIE,Vol.7529, pp.362-369, Jan 2010. doi: https://doi.org/10.1117/12.840234
  7. Xing, Yafei, Beatrice Pesquet-Popescu, and Frederic Dufaux. "Compression of computer generated phase-shifting hologram sequence using AVC and HEVC," Applications of Digital Image Processing XXXVI,SPIE, Vol.8856, pp.531-538, Sep 2013. doi: https://doi.org/10.1117/12.2027148
  8. JPEG (ISO/IEC JTC1/SC29/WG1), "JPEG Pleno: Interfere codec V1.00 interface description," WG1M94003, November 2021.
  9. Jiao, Shuming, et al. "Compression of phase-only holograms with JPEG standard and deep learning," Applied Sciences, Vol.8, No.8 pp.1258, July 2018. doi: https://doi.org/10.3390/app8081258
  10. Tu, Han-Yen, Ching-Huang Hsieh, and Huong-Giang Hoang. "Compression of phase image for three-dimensional object," 2014 21st International Workshop on Active-Matrix Flatpanel Displays and Devices (AM-FPD), IEEE, pp.97-100, July 2014. doi: https://doi.org/10.1109/AM-FPD.2014.6867135
  11. Shi, Liang, et al. "Towards real-time photorealistic 3D holography with deep neural networks," Nature, Vol.591, No.7849, pp.234-239, Mar 2021. doi: https://doi.org/10.1038/s41586-021-03476-5
  12. Wang, Yujie, et al. "Joint Neural Phase Retrieval and Compression for Energy-and Computation-Efficient Holography on the Edge,." Association for Computing Machinery, Vol.41, No.4, pp.1-16, July 2022. doi: https://doi.org/10.1145/3528223.3530070
  13. Shechtman, Yoav, et al. "Phase retrieval with application to optical imaging: a contemporary overview,." IEEE signal processing magazine, Vol.32, No.3, pp.87-109, April 2015. doi: https://doi.org/10.1109/MSP.2014.2352673
  14. Maimone, Andrew, Andreas Georgiou, and Joel S. Kollin. "Holographic near-eye displays for virtual and augmented reality." ACM Transactions on Graphics (Tog), Vol.36, No.4, pp.1-16, Aug 2017. doi: https://doi.org/10.1145/3072959.3073624
  15. Peng, Yifan, et al. "Neural holography with camera-in-the-loop training,." ACM Transactions on Graphics (TOG), Vol.39, No.6, pp.1-14, Dec 2020. doi: https://doi.org/10.1145/3414685.3417802
  16. Hsueh, Chung-Kai, and Alexander A. Sawchuk. "Computer-generated double-phase holograms." Applied optics, Vol.17, No.24, pp. 3874-3883, 1978. doi: https://doi.org/10.1364/AO.17.003874
  17. Reichelt, Stephan, and Norbert Leister. "Computational hologram synthesis and representation on spatial light modulators for real-time 3D holographic imaging," Journal of Physics: Conference Series, IOP Publishing,Vol.415, No.1, pp.012038, 2013. doi: https://doi.org/10.1088/1742-6596/415/1/012038
  18. Sullivan, Gary J., et al. "Overview of the high efficiency video coding (HEVC) standard." IEEE Transactions on circuits and systems for video technology, Vol.22, No.12, pp.1649-1668, Dec 2012. doi: https://doi.org/10.1109/TCSVT.2012.2221191
  19. Bross, Benjamin, et al. "Overview of the versatile video coding (VVC) standard and its applications," IEEE Transactions on Circuits and Systems for Video Technology, Vol.31, No.10, pp.3736-3764, Oct 2021. doi: https://doi.org/10.1109/TCSVT.2021.3101953
  20. Balle, Johannes, Valero Laparra, and Eero P. Simoncelli. "End-to-end optimized image compression," International Conference on Learning Representations, (Nov 2016. doi: https://doi.org/10.48550/arXiv.1611.01704
  21. Balle, Johannes, et al. "Variational image compression with a scale hyperprior," International Conference on Learning Representations, 2018. doi: https://doi.org/10.48550/arXiv.1802.01436
  22. Minnen, David, Johannes Balle, and George D. Toderici. "Joint autoregressive and hierarchical priors for learned imagecompression," Advances in Neural Information Processing Systems, pp.10771-10780, 2018. doi: https://doi.org/10.48550/arXiv.1809.02736
  23. Cheng, Zhengxue, et al. "Learned image compression with discretized gaussian mixture likelihoods and attention modules," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.7939-7948, 2020. doi: https://doi.org/10.48550/arXiv.2001.01568
  24. Zou, Renjie, Chunfeng Song, and Zhaoxiang Zhang. "The Devil Is in the Details: Window-based Attention for Image Compression." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.17492-17501, Mar 2022. doi: https://doi.org/10.48550/arXiv.2203.08450
  25. Yuan, Zhongzheng, et al. "Block-based Learned Image Coding with-Convolutional Autoencoder and Intra-Prediction Aided Entropy Coding." 2021 Picture Coding Symposium (PCS), IEEE, pp.1-5, June 2021. doi: https://doi.org/10.1109/PCS50896.2021.9477503
  26. Brand, Fabian, Jurgen Seiler, and Andre Kaup. "Intra-frame coding using a conditional autoencoder." IEEE Journal of Selected Topics in Signal Processing, Vol.15, No.2, pp.354-365, Feb 2020. doi: https://doi.org/10.1109/JSTSP.2020.3034768
  27. Wu, Yaojun, et al. "Learned block-based hybrid image compression," IEEE Transactions on Circuits and Systems for Video Technology, Vol.32, No.6. pp.3978-3990, Dec 2020. doi: https://doi.org/10.48550/arXiv.2012.09550
  28. G. Bjontegaard, "Improvements of the BD-PSNR model," Doc. VCEG-AI11, ITU-T SG16/Q6 VCEG, 35th meeting, Berlin, 2008.
  29. Oh, Kwan-Jung, Jinwoong Kim, and Hui Yong Kim. "A New Objective Quality Metric for Phase Hologram Processing," ETRI Journal, Vol.44, No.1, pp.94-104, Dec 2022. doi: https://doi.org/10.4218/etrij.2021-0209
  30. Kim, Yeongwoong, et al. "Latent Shifting and Compensation for Learned Video Compression." Journal of Broadcast Engineering, Vol.27, No.1, pp.31-43, 2022 Jan. https://doi.org/10.5909/JBE.2022.27.1.31
  31. Agustsson, Eirikur, and Radu Timofte. "Ntire 2017 challenge on single image super-resolution: Dataset and study." Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp.126-135, Aug 2017. doi: https://doi.org/10.1109/CVPRW.2017.150
  32. Reference software of HEVC (HM), https://hevc.hhi.fraunhofer.de/svn/svn_HEVCSoftware/tags/HM-16.20/ (accessed Dec, 31, 2020)
  33. Reference software of VVC (VTM), https://vcgit.hhi.fraunhofer.de/jvet/VVCSoftware_VTM/ (accessed Oct, 12, 2021)