(50-3) 19 * << * >> * Russian * English * Content * All Issues

Research on an image color restoration method for old art films
H.L. Zhang1*, C.J. Shao2

1 Shanghai Dianji University, Shanghai 200240, China;
2 Shanghai Polytechnic University, Shanghai 201209, China;
* Corresponding Author

  Full text (PDF)

DOI: 10.18287/COJ1781

Article ID: 1781

Language: English

Abstract:
The preservation and restoration of old art films have certain practical value. Focusing on the color restoration of old art films, this paper introduced the same mapping loss on the basis of a cycle-consistent generative adversarial network, which enables the algorithm to capture more image details and achieve better transfer results. The old art films Roman Holiday and Tracks in the Snowy Forest were used as experimental data to verify the color restoration effect of the improved cycle-consistent generative adversarial network algorithm. It was found that compared with the generative adversarial network and cycle-consistent generative adversarial network algorithms, the improved cycle-consistent generative adversarial network algorithm was superior. It achieved a peak signal-to-noise ratio of 26.874, a structural similarity index measure of 0.665, a learned perceptual image patch similarity of 0.212, and a Frechet inception distance of 117.652 for Roman Holiday. Moreover, it achieved a peak signal-to-noise ratio of 22.794, a structural similarity index measure of 0.585, a learned perceptual image patch similarity of 0.247, and a Frechet inception distance of 119.265 for Tracks in the Snowy Forest. It also achieved better results in comparison with existing image color restoration methods. The results demonstrate the usability of the improved cycle-consistent generative adversarial network algorithm in color restoration of old art films, which can be applied in practice.

Keywords:
color restoration, old art film, generative adversarial network, peak signal-to-noise ratio.

Acknowledgements:

Citation:
Zhang HL, Shao CJ. Research on an image color restoration method for old art films. Computer Optics 2026; 50(3): 1781. doi:10.18287/COJ1781.

References:

  1. Zheng X. Research on marketing strategies of domestic movies under the perspective of 4V theory: taking \"Full River Red\" as an example. SHS Web Conf 2024; 188: 03004. doi:10.1051/shsconf/202418803004.
  2. Renaudeau A, Seng T, Carlier A, Pierre F, Lauze F, Aujol JF, Durou JD. Learning defects in old movies from manually assisted restoration. In: Proc 25th Int Conf Pattern Recognit (ICPR); 2021. doi:10.1109/ICPR48806.2021.9413196.
  3. Dai M, Zhang W, Zheng W. Digital stabilization method for old movies based on MobileSAM and optical flow. Multimed Syst 2025; 31(3): 1-12. doi:10.1007/s00530-025-01740-6.
  4. Cao C, Dong Q, Fu Y. ZITS++: image inpainting by improving the incremental transformer on structural priors. IEEE Trans Pattern Anal Mach Intell 2023; 45(10): 12667-12684. doi:10.1109/TPAMI.2023.3280222.
  5. Xian J, Xu X, Xian Y, Xian C. Image inpainting algorithm based on hybrid encoding and mask space modulation. J South China Univ Technol Nat Sci Ed 2025; 53(3): 31-39. doi:10.12141/j.issn.1000-565X.240155.
  6. Sompoppokasest S, Siriborvornratanakul T. Lightweight image inpainting model for removing unwanted objects from residential real estate indoor scenes. Multimed Tools Appl 2024; 83(34): 80389-80410. doi:10.1007/s11042-024-18605-1.
  7. Yuan J, Wu H, Wu F. Novel dual U-Net generative adversarial network for image inpainting. Int J Pattern Recognit Artif Intell 2024; 38(6): 2454006. doi:10.1142/S0218001424540065.
  8. Cai J, Jiang J, Wang Y, Zheng J, Xu H. Image inpainting via smooth Tucker decomposition and low-rank Hankel constraint. Int J Comput Appl 2023; 45(6): 421-432. doi:10.1080/1206212X.2023.2219836.
  9. Ning T, Huang G, Li J, Huang S. Complex image inpainting of cultural relics integrating multi-stage structural features and spatial textures. Pattern Anal Appl 2025; 28(2): 1-18. doi:10.1007/s10044-025-01434-9.
  10. Andriyanov N, Belyanchikov A, Vasiliev K, Dementiev V. Restoration of spatially inhomogeneous images based on doubly stochastic filters. In: Proc VIII Int Conf Inform Technol Nanotechnol (ITNT); 2022. 4 pp. doi:10.3103/S8756699022050028.
  11. Sun P, Jiang Y, Chen S, Zhang S, Peng B, Luo P, Yuan Z. Autoregressive model beats diffusion: LLaMA for scalable image generation. arXiv 2024; arXiv:2406.06525.
  12. Faye B, Azzag H, Lebbah M, Bouchaffra D. Adaptive context normalization: a boost for deep learning in image processing. In: Proc 2024 IEEE Int Conf Image Process (ICIP); 2024. pp. 1037-1043.
  13. Chang R, Liu G, Qian Y, Tang H, Wang G, Bavirisetti DP. GDNet: low-light image enhancement network based on Ghost-block and unique image decomposition. J Supercomput 2025; 81(1): 160. doi:10.1007/s11227-024-06683-9.
  14. Miao J, Kou K, Yang Y, Yang L, Han J. Quaternion matrix completion using untrained quaternion convolutional neural network for color image inpainting. Signal Process 2024; 221: 109635. doi:10.1016/j.sigpro.2023.109635.
  15. Miao W, Wang L, Lu H, Huang K, Shi X, Liu B. ITrans: generative image inpainting with transformers. Multimed Syst 2024; 30(1): 1-12. doi:10.1007/s00530-023-01211-w.
  16. Zhu JY, Park T, Isola P, Efros AA. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proc IEEE Int Conf Comput Vis (ICCV); 2017. pp. 2242-2251. doi:10.1109/ICCV.2017.244.
  17. Anjum U, Afzal U, Hussain A, Hussain I, Channa BA, Noorwali A, Shah SA. JPEG image compression using multiple core strategy in FPGA achieving high peak signal-to-noise ratios. In: Proc Int Congr Adv Technol Eng (ICOTEN); 2021. pp. 1-6. doi:10.1109/ICOTEN52080.2021.9493460.
  18. Kang M, Baek J. SAR image change detection via multiple-window processing with structural similarity. Sensors 2021; 21(19): 6645. doi:10.3390/s21196645.
  19. Diaw M, Retraint F, Morain-Nicolier F, Delahaies A, Landre J. New statistic detector for structural image similarity. IEEE Trans Signal Process 2025; 73: 1168-1183. doi:10.1109/TSP.2025.3543207.
  20. Siddiqui AA, Tirunagari S, Zia T, Windridge D. Latent diffusion approach to visual attribution in medical imaging. Sci Rep 2025; 14(1): 962. doi:10.1038/s41598-024-81646-x.
  21. Arjovsky M, Chintala S, Bottou L. Wasserstein generative adversarial networks. Proc 34th Int Conf Mach Learn (ICML); 2017; 70: 214-223.
  22. Johnson J, Alahi A, Fei-Fei L. Perceptual losses for real-time style transfer and super-resolution. In: Proc Eur Conf Comput Vis (ECCV); 2016. pp. 694-711. doi:10.1007/978-3-319-46475-6_43.

151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20