Research into neural networks as a method for image compression and archiving

This article explores a method for storing images by training a neural network on a single image and storing its weights as a compact representation. This approach significantly reduces the amount of data stored while maintaining acceptable visual quality. Model parameters and training settings are analyzed to optimize recovery quality. The basic idea of the approach is that a trained model stores its weights, which act as a compact representation of the original image. When reconstruction is required, the weights are reloaded into the network to restore the visual content. Experimental results show that optimizing the network architecture and color space (YCbCr) enables high compression ratios – up to 29.4 while maintaining visual quality close to the original (MSE ≈ 10-5). However, the authors note a significant drawback of the method: long training time and significant computational costs, making it less effective than traditional compression algorithms for practical real-time applications. Nevertheless, the approach demonstrates potential for tasks where preserving fine image details is critical, such as data archiving or video stream compression.

1. Podberezkin A.A., Ostroukh A.V., Borzenkov A.M., Shmonin A.M., Pronin C.B. Research methods for digitalization of transport systems using artificial intelligence. Transportation and Information Technologies in Russia. 2025;15(3):141–166. (In Russ.). https://doi.org/10.12731/3033-5965-2025-15-3-396

2. Archana R., Jeevaraj P.S.E. Deep learning models for digital image processing: a review. Artificial Intelligence Review. 2024;57(1). https://doi.org/10.1007/s10462-023-10631-z

3. Jiang F., Tao W., Liu Sh., et al. An End-to-End Compression Framework Based on Convolutional Neural Networks. IEEE Transactions on Circuits and Systems for Video Technology. 2018;28(10):3007–3018. https://doi.org/10.1109/TCSVT.2017.2734838

4. Sun H., Yu L., Katto J. End-to-end learned image compression with quantized weights and activations. arXiv. URL: https://doi.org/10.48550/arXiv.2111.09348 [Accessed 22nd February 2026].

5. Lyozin I., Solovyov A. Performing an Image Compression by Using the Multilayer Perceptron. Izvestia of Samara Scientific Center of the Russian Academy of Sciences. 2016;18(4-4):770–773. (In Russ.).

6. Podberezkin A.A., Borzenkov A.M., Volkov A.M., Pronin Ts.B., Ostroukh A.V. Application of a Genetic Algorithm for Traffic Signal Optimization Considering Regulatory Requirements and Public Transport Priority. Modern High Technologies. 2025;(9):181–185. (In Russ.). https://doi.org/10.17513/snt.40504

7. Deng H., Liu H., Wang F., Wang Zh., Wang Y. Image Compression Based on Genetic Algorithm and Deep Neural Network. In: Bio-inspired Computing – Theories and Applications: 11th International Conference, BIC-TA 2016: Part I, 28–30 October 2016, Xi'an, China. Singapore: Springer; 2016. P. 417–424. https://doi.org/10.1007/978-981-10-3611-8_36

8. Liu J., Sun H., Katto J. Learned image compression with mixed transformer-CNN architectures. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 17–24 June 2023, Vancouver, BC, Canada. IEEE; 2023. P. 14388–14397. https://doi.org/10.1109/CVPR52729.2023.01383

9. Shindo T., Yamada K., Watanabe T., Watanabe H. Image coding for machines with edge information learning using segment anything. In: 2024 IEEE International Conference on Image Processing (ICIP), 27–30 October 2024, Abu Dhabi, United Arab Emirates. IEEE; 2024. P. 3702–3708. https://doi.org/10.1109/ICIP51287.2024.10647785

10. Li X., Ren Y., Jin X., et al. Diffusion models for image restoration and enhancement: A comprehensive survey. International Journal of Computer Vision. 2025;133(11):8078–8108. https://doi.org/10.1007/s11263-025-02570-9

11. Zafari A., Chen X., Jalali Sh. DeCompress: Denoising via Neural Compression. In: 2025 IEEE International Symposium on Information Theory (ISIT), 22–27 June 2025, Ann Arbor, MI, USA. IEEE; 2025. P. 1–6. https://doi.org/10.1109/ISIT63088.2025.11195310

12. Nguyen N., Nguyen Th., Bose B. Perception-based Image Denoising via Generative Compression. arXiv. URL: https://doi.org/10.48550/arXiv.2602.11553 [Accessed 22nd February 2026].