Abstract
GAN-based image colorization techniques are capable of producing highly realistic color in real-time. Subjective assessment of these approaches has demonstrated that humans are unable to differentiate between a true RGB image and a colorized image. In this work, we evaluate the fidelity of such colorization and for the first time analyze the GAN-based image colorization scheme in the context of image compression. Our analysis shows that the palette (set of colors) recommended by the GAN-based framework is very limited even for highly realistic interactive colorization. We propose two novel methods of automatic palette generation that allows for the GAN-based framework to be useful for image compression. We demonstrate that provided true colors at a few pixel locations, GAN-based approach results in good spread of color to other image regions. Subjective analysis on a number of public datasets shows that the current system has low fidelity but performs better than JPEG at low data rate regimes.
Similar content being viewed by others
References
BT RECOMMENDATION ITU-R (2002) Methodology for the subjective assessment of the quality of television pictures
Cheng Z, Yang Q, Sheng B (2015) Deep colorization. In: Proceedings of the IEEE International Conference on Computer Vision, pp 415–423
Christopoulos C, Skodras A, Ebrahimi T (2000) The JPEG2000 still image coding system: an overview. IEEE Trans Consum Electron 46(4):1103–1127. https://doi.org/10.1109/30.920468
Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph-based image segmentation. International journal of computer vision 59(2):167–181
Girod B (1993) What’s wrong with mean-squared error?, Digital images and human vision, 207–220
Gygli M, Grabner H, Riemenschneider H, Nater F, Van Gool L (2013) The interestingness of images. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1633–1640
He Y, Xuan Y, Chen W, Fu X (2009) Subjective image quality assessment: A method based on signal detection theory. In: 2009 IEEE International Conference on Systems, Man and Cybernetics, pp 4915–4919
Khosla A, Das Sarma A, Hamid R (2014) What makes an image popular?. In: Proceedings of the 23rd international conference on World wide web, ACM, pp 867–876
Kikuchi H, Huttunen H, Hwang J, Yukawa M, Muramatsu S, Shin J (2012) Color-tone similarity on digital images. In: Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, IEEE, pp 1–4
Leger A M, Omachi T, Wallace G K (1991) JPEG still picture compression algorithm. Opt Eng 30(7):947–955
Mantiuk R K, Tomaszewska A, Mantiuk R (2012) Comparison of four subjective methods for image quality assessment. In: Computer graphics forum, vol 31, Wiley Online Library, pp 2478–2491
Mohammadi P, Ebrahimi-Moghadam A, Shirani S (2014) Subjective and objective quality assessment of image: A survey. arXiv:1406.7799
Rehman A, Wang Z (2012) Reduced-reference image quality assessment by structural similarity estimation. IEEE Trans Image Process 21(8):3378–3389
Rippel O, Bourdev L (2017) Real-time adaptive image compression. arXiv:1705.05823
Thakur N, Devi S (2011) A new method for color image quality assessment. International Journal of Computer Applications 15(2):10–17
Wang Z, Bovik A C (2009) Mean squared error: Love it or leave it? a new look at signal fidelity measures. IEEE signal processing magazine 26(1):98–117
Wang Z, Bovik A C, Lu L (2002) Why is image quality assessment so difficult?. In: ICASSP, vol 4, pp 3313–3316
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13(4):600–612
Zhang R, Isola P, Efros AA (2016) Colorful image colorization. In: European Conference on Computer Vision, Springer, pp 649–666
Zhang R, Zhu J-Y, Isola P, Geng X, Lin AS, Yu T, Efros AA (2017) Real-time user-guided image colorization with learned deep priors. arXiv:1705.02999
Acknowledgements
The authors thank the participants of the experiment for subjective image quality assessment and acknowledge the computational support provided by the Supercomputing Research and Education Centre (ScREC) at National University of Sciences and Technology (NUST), Islamabad, Pakistan.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Fatima, A., Hussain, W. & Rasool, S. Grey is the new RGB: How good is GAN-based image colorization for image compression?. Multimed Tools Appl 80, 3775–3791 (2021). https://doi.org/10.1007/s11042-020-09861-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09861-y