Features of reconstruction of continuous lacunas in images
Abstract
This work is a review of the experience in solving the problems of retouching and reconstructing the content of continuous lacunas in images. Restoring continuous (long) gaps is significantly more difficult than doing similar work with sparse data, since prolonged loss leads to the loss of signal phase and dynamics. The main problem is that, given the significant size of the lacunas, most algorithms cannot maintain sufficient continuity and consistency of the signal or image structure. It has been shown that image inpainting methods or neural networks work well when retouching or masking the content of a gap. And if it is necessary to restore the contents of the lacunas, it is preferable to use methods that operate in the frequency domain (for example, the interpolation method of the sequentially calculated Fourier spectrum).
Аннотация (на русском)
Особенности реконструкции сплошных лакун на изображениях
Эта работа является обзором опыта по решению задач ретуширования и реконструкции содержимого сплошных лакун на изображениях. Восстановление сплошных (длинных) пропусков значительно сложнее, чем аналогичная работа с разреженными данными, так как при длительной потере теряется фаза и динамика сигнала. Основная проблема заключается в том, что при значительных размерах лакун большинство алгоритмов не могут сохранить достаточную непрерывность и согласованность структуры сигнала или изображения. Показано что при ретушировании или маскировке содержимого лакуны хорошо работают методы image inpainting или нейронные сети. А если необходимо восстановить содержимое лакун, то предпочтительным является использование методов, работающих в частотной области (например: метод интерполяции последовательно вычисляемого спектра Фурье).
Funding
This work was carried out within the framework of a state assignment for the V.A. Kotelnikov Institute of Radio Engineering and Electronics of the Russian Academy of Sciences.
For citation
Kokoshkin A.V. Features of reconstruction of continuous lacunas in images // Journal of Radio Electronics. – 2026. – № 10. https://doi.org/10.30898/1684-1719.2026.10.4 (In Russian)
References
- Zverev V.A. Radiooptics. Moscow, “Sovetskoe Radio” – 1975. – P. 304. (In Russian)
- Aksenov A.P. Mathematical Analysis. Fourier Series. Fourier Integral. Summation of Divergent Series. Textbook. – 1999. – P. 86. (In Russian)
- Strakhov V.N., Strakhov A.V. Approximation Approach to Solving Problems of Gravimetry and Magnetometry //Russian Journal of Earth Sciences. – 1999. – Vol. 1. – No. 4. (In Russian)
- Shcherba E.V. Application analysis of interpolation and extrapolation methods as used for image restoration. // Computer Optics. – 2009 – Vol. 33. – No. 3 – P. 336-339. (In Russian)
- Ashkenazy V. O. Spline Surfaces. Fundamentals of Theory and Computational Algorithms //Tver: Tver State University. – 2003. – P. 82. (In Russian)
- Nesterenko E. A. The possibility of using a spline surface to construct surfaces based on survey data //Notes of the Mining Institute. – 2013. – Vol. 204. – P. 127-133. (In Russian)
- Qureshi M. A. et al. A critical survey of state-of-the-art image inpainting quality assessment metrics //Journal of Visual Communication and Image Representation. – 2017. – Vol. 49. – P. 177-191. https://doi.org/10.1016/j.jvcir.2017.09.006
- Chen Z. et al. Structure-aware image inpainting using patch scale optimization // Journal of Visual Communication and Image Representation. – 2016. – Vol. 40. – P. 312-323. http://dx.doi.org/10.1016/j.jvcir.2016.06.029
- Movavi Photo Editor. Source: (https://www.movavi.com/photo-editor/)
- Astafyeva N. M., Raev M. D., Sharkov E. A. Global radiothermal fields for the atmosphere-ocean system using microwave-satellite instruments // Issledovanie Zemli iz Kosmosa. – 2006. – No. 4. – P. 64–70. (In Russian)
- Ermakov DM, Sharkov EA, Chernushich AP. Multisensor algorithm for satellite radio thermal imaging. // Issledovanie Zemli iz Kosmosa 2006; 4: 64-70. (In Russian)
- Bregman L. M. Finding a common point of convex sets using the method of successive projection // Reports of the Academy of Sciences. – Russian Academy of Sciences, 1965. – Vol. 162. – No. 1. – Pp. 487–490. (In Russian)
- Gurin L. G., Polyak B. T., Raik E. V. Projection methods for finding a common point of convex sets // Journal of Computational Mathematics and Mathematical Physics. – 1967. – Vol. 7. – No. 6. – Pp. 1211–1228. (In Russian)
- Youla D. C., Webb H. Image Restoration by the Method of Convex Projections: Part 1. Theory // IEEE transactions on medical imaging. – 1982. – Vol. 1. – №. 2. – P. 81-94.
- Kokoshkin AV, Korotkov VA, Korotkov KV, Novichikhin EP. Retouching and restoration of missing image fragments by means of the iterative calculation of their spectra. // Computer Optics – 2019. – Vol..43 – №. 6. – P. 1030-1040. https://doi.org/10.18287/2412-6179-2019-43-6-1030-1040 (In Russian)
- Kokoshkin A.V. Sparse Image Interpolation Methods Working in the Frequency Domain. // Journal of Radio Electronics. – 2023. – №3. https://doi.org/10.30898/1684-1719.2023.3.10 (In Russian)
- Kokoshkin A.V., Korotkov V.A., Novichikhin E.P. Reconstruction of Acoustic Signals According to Incomplete Data // J. of Communications Technology and Electronics. – 2020. – Vol. 65. – №. 12. – P. 1399–1406. http://dx.doi.org/10.1134/S1064226920120104
- Cherepenin V.A., Zhuravlev A.V., Chizh M.A., Kokoshkin A.V., Korotkov V.A., Korotkov K.V., Novichikhin E.P. Reconstruction of Subsurface Radio Holograms Fully and Partially Measured by Different Methods. // Journal of Communications Technology and Electronics – 2017. – Vol. 62. – No. 7 – P. 780–787. https://doi.org/10.1134/S1064226917070038b
- A. V. Kokoshkin, V. A. Korotkov, K. V. Korotkov, E. P. Novichihin. Application of digital image processing methods for the goal of restoration of fine art objects. // Journal of Radio Electronics. – 2018. – No. 9. https://doi.org/10.30898/1684-1719.2018.9.16
- Dedkova A. A., Chernyshev A. K., Kokoshkin A. V. Algorithms for preprocessing surface maps for ion beam correction // Journal of Technical Physics. – 2026. – Vol. 96. – No. 10. – Pp. 2059-2068. https://doi.org/10.61011/JTF.2026.10.63624.149-26