International Journal of Internet, Broadcasting and Communication

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Denoising Diffusion Null-space Model and Colorization based Image Compression

  • Indra Imanuel (Dept. Computer Engineering, Dongseo University) ;
  • Dae-Ki Kang (Dept. Computer Engineering, Dongseo University) ;
  • Suk-Ho Lee (Dept. Computer Engineering, Dongseo University)
  • Received : 2024.03.05
  • Accepted : 2024.03.19
  • Published : 2024.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Image compression-decompression methods have become increasingly crucial in modern times, facilitating the transfer of high-quality images while minimizing file size and internet traffic. Historically, early image compression relied on rudimentary codecs, aiming to compress and decompress data with minimal loss of image quality. Recently, a novel compression framework leveraging colorization techniques has emerged. These methods, originally developed for infusing grayscale images with color, have found application in image compression, leading to colorization-based coding. Within this framework, the encoder plays a crucial role in automatically extracting representative pixels-referred to as color seeds-and transmitting them to the decoder. The decoder, utilizing colorization methods, reconstructs color information for the remaining pixels based on the transmitted data. In this paper, we propose a novel approach to image compression, wherein we decompose the compression task into grayscale image compression and colorization tasks. Unlike conventional colorization-based coding, our method focuses on the colorization process rather than the extraction of color seeds. Moreover, we employ the Denoising Diffusion Null-Space Model (DDNM) for colorization, ensuring high-quality color restoration and contributing to superior compression rates. Experimental results demonstrate that our method achieves higher-quality decompressed images compared to standard JPEG and JPEG2000 compression schemes, particularly in high compression rate scenarios.

Keywords

Acknowledgement

This work was supported by Dongseo University, "Dongseo Cluster Project" Research Fund of 2023(DSU- 20230004)

References

  1. L. Cheng and S. V. N. Vishwanathan, "Learning to compress images and videos," in Proc. Int. Conf. Mach. Learn., Vol. 227, pp. 161-168, 2007. DOI: https://doi.org/10.1145/1273496.1273517
  2. X. He, M. Ji, and H. Bao, "A unified active and semi-supervised learning framework for image compression," in Proc. IEEE Comput. Vis. Pattern Recognit., pp. 65-72, Jun. 2009. DOI: https://doi.org/10.1109/CVPR.2009.5206835
  3. L. Tan, Y. Zeng, and W. Zhang, "Research on Image Compression Coding Technology," in Proc. 3rd International Conference on Data Mining, Communications and Information Technology (DMCIT 2019), Vol. 1284, pp.1-7, 2019. DOI: https://doi.org/10.1088/1742-6596/1284/1/012069
  4. G.K. Wallace, "The JPEG still picture compression standard," IEEE Transactions on Consumer Electronics, Vol. 38, Issue 1, pp. 18-34, 1992, DOI: https://doi.org/10.1109/30.125072
  5. T. Miyata, Y. Komiyama, Y. Inazumi, and Y. Sakai, "Novel inverse colorization for image compression," in Proc. Picture Coding Symp., 2009, pp. 1-4. DOI: https://doi.org/10.1109/PCS.2009.5167413
  6. S. Ono, T. Miyata, and Y. Sakai, "Colorization-based coding by focusing on characteristics of colorization bases," in Proc. Picture Coding Symp. Dec. 2010, pp. 230-233. DOI: https://doi.org/10.1109/PCS.2010.5702473
  7. S. Lee, S.-W. Park, P. Oh, and M.-G. Kang, "Colorization-Based Compression Using Optimization," IEEE Trans. Image Processing, Vol. 22, No. 7, pp. 2627-2635, 2013. DOI: https://doi.org/10.1109/TIP.2013.2253486
  8. A. Levin, D. Lischinski, and Y. Weiss, "Colorization using optimization,"ACM Trans. Graph., vol. 23, no. 3, pp. 689-694, Aug. 2004. DOI: https://doi.org/10.1145/1015706.1015780
  9. Y. Wang, J. Yu, J. Zhang, "Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model," in Proc. ICML (2023), 2023. DOI: https://doi.org/10.48550/arXiv.2212.00490
  10. J. Schwab, S. Antholzer, and M. Haltmeier, "Deep null space learning for inverse problems: convergence analysis and rates," Inverse Problems, Vol. 35, No. 2, pp.1-13, 2019. DOI: https://doi.org/10.1088/1361-6420/aaf14a
  11. B. Kawar, M. Elad, S. Ermon, and J. Song, "Denoising diffusion restoration models," in Proc. ICML(2022), 2022. DOI: https://doi.org/10.48550/arXiv.2201.11793
  12. J. Song, C. Meng, and S. Ermon, "Denoising diffusion implicit models," In Proc. International Conference on Learning Representations(ICLR), 2021. DOI:https://doi.org/10.48550/arXiv.2010.02502
  13. Z. Cheng, H. Sun, M. Takeuchi, and J. Katto, "Learned image compression with discretized gaussian mixture likelihoods and attention modules," In Proc. of the IEEE/CVF conference on computer vision and pattern recognition (pp. 7939-7948). 2020. DOI:https://doi.org/10.1109/CVPR42600.2020.00796
  14. J. Ho, A. Jain, and P. Abbeel, "Denoising diffusion probabilistic models," arXiv Preprint arXiv:2006.11239, 2020. DOI:https://doi.org/10.48550/arXiv.2006.11239
  15. International Commission on Illumination. https://cie.co.at.