cahtНаучный вестник МГТУ ГАCivil Aviation High Technologies2079-06192542-0119Moscow State Technical University of Civil Aviation (MSTU CA)10.26467/2079-0619-2023-26-5-30-41caht-2231Research ArticleТРАНСПОРТНЫЕ СИСТЕМЫTRANSPORTATION SYSTEMSОбеспечение визуальной когерентности в обучающих системах дополненной реальности с учетом авиакосмической спецификиVisual coherence in augmented reality training systems considering aerospace specific featuresГорбуновА. Л.GorbunovA. L.

Горбунов Андрей Леонидович, кандидат технических наук, доцент, доцент кафедры управления воздушным движением

Москва

Andrey L. Gorbunov, Candidate of Technical Sciences, Associate Professor, Associate Professor of the Air Traffic Management Chair

Moscow

a.gorbunov@mstuca.aeroЛиЮ.LiYu.

Ли Юньхань, аспирантка

Москва

Yunhan Li, Postgraduate Student

Moscow

antatanoe@gmail.comМосковский государственный технический университет гражданской авиацииРоссияMoscow State Technical University of Civil AviationRussian Federation2023301020232653041Copyright © Горбунов А.Л., Ли Ю., 20232023Горбунов А.Л., Ли Ю.Gorbunov A.L., Li Y.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://avia.mstuca.ru/jour/article/view/2231

В мае 2022 года саудовская правительственная структура Saudi Arabian Military Industries приобрела обучающую платформу дополненной реальности для летчиков, в сентябре корпорация Boeing начала разработку тренажера пилота дополненной реальности, в ноябре стартовал аналогичный проект ведущего британского разработчика авиационной техники BAE Systems. Эти факты позволяют уверенно говорить о начале новой эпохи авиационных тренажеров – тренажеров с применением технологии дополненной реальности. Одно из перспективных преимуществ данной технологии – возможность безопасного моделирования опасных ситуаций в реальном мире. Необходимым условием использования этого преимущества является обеспечение визуальной когерентности сцен дополненной реальности: виртуальные объекты должны быть неотличимы от реальных. Все мировые IT-лидеры рассматривают дополненную реальность как следующую «большую волну» радикальных изменений в цифровой электронике, поэтому визуальная когерентность становится ключевым вопросом для будущего IT, а в аэрокосмических приложениях визуальная когерентность уже приобрела практическое значение. В РФ имеет место серьезное отставание в изучении проблематики визуальной когерентности в целом и для авиатренажеров дополненной реальности в частности: на момент публикации авторам удалось обнаружить в российском научном пространстве только две работы по теме, тогда как за рубежом их число уже около тысячи. Цель настоящей обзорной статьи – создать условия для купирования проблемы. Визуальная когерентность зависит от многих факторов: освещения, цветового тона, теней от виртуальных объектов на реальных, взаимных отражений, текстур виртуальных поверхностей, оптических аберраций, конвергенции и аккомодации и др. В статье анализируются публикации, посвященные методам оценки условий освещенности и цветового тона реальной сцены и переноса таковых на виртуальные объекты с использованием зондов и по отдельным изображениям, а также по рендерингу виртуальных объектов в сценах дополненной реальности, в том числе с применением нейросетей.

In May 2022, Saudi Arabian Military Industries, a Saudi government agency, acquired an augmented reality training platform for pilots. In September, the Boeing Corporation began the development of an augmented reality pilot simulator. In November, a similar project was launched by BAE Systems, a leading British developer of aeronautical engineering. These facts allow us to confidently speak about the beginning of a new era of aviation simulators – simulators using the augmented reality technology. One of the promising advantages of this technology is the ability to safely simulate dangerous situations in the real world. A necessary condition for using this advantage is to ensure the visual coherence of augmented reality scenes: virtual objects must be indistinguishable from real ones. All the global IT leaders consider augmented reality as the subsequent surge of radical changes in digital electronics, so visual coherence is becoming a key issue for the future of IT, and in aerospace applications, visual coherence has already acquired practical significance. The Russian Federation lags far behind in studying the problems of visual coherence in general and for augmented reality flight simulators in particular: at the time of publication the authors managed to find only two papers on the subject in the Russian research space, while abroad their number is already approximately a thousand. The purpose of this review article is to create conditions for solving the problem. Visual coherence depends on many factors: lighting, color tone, shadows from virtual objects on real ones, mutual reflections, textures of virtual surfaces, optical aberrations, convergence and accommodation, etc. The article reviews the publications devoted to methods for assessing the conditions of illumination and color tone of a real scene and transferring them to virtual objects using various probes and by individual images, as well as by rendering virtual objects in augmented reality scenes, using neural networks.

авиационные тренажерыдополненная реальностьвизуальная когерентностьflight simulatorsaugmented realityvisual coherenceReferencesГорбунов А.Л. Визуальная когерентность в дополненной реальности // Advanced Engineering Research. 2023. № 2. С. 180–190. DOI: 10.23947/2687-1653-2023-23-2-180-190Gorbunov, А.L. (2023). Visual coherence for augmented reality. Advanced Engineering Research, no. 2, pp. 180–190. DOI: 10.23947/2687-1653-2023-23-2-180-190 (in Russian)Горбунов А.Л. Визуальная однородность сцен дополненной реальности // Запись и воспроизведение объемных изображений в кинематографе и других областях: сборник докладов IX Международной научно-практической конференции. Москва, 17–18 апреля 2017 г. М.: ВГИК им. С.А. Герасимова, 2017. С. 235–239.Gorbunov, А.L. (2017). Visual homogeneity of augmented reality scenes. In: Zapis i vosproizvedeniye obyemnykh izobrazheniy v kinematografe i drugikh oblastyakh: sbornik dokladov IX Mezhdunarodnoy nauchno-prakticheskoy konferentsii. Moscow: VGIK im. S.A. Gerasimova, pp. 235–239. (in Russian)Hughes C. The psychometrics of cybersickness in augmented reality / C. Hughes, C. Fidopiastis, K. Stanney, P. Bailey, E. Ruiz [Электронный ресурс] // Frontiers in Virtual Reality. 2020. Vol. 1. ID: 602954. DOI: 10.3389/frvir.2020.602954 (дата обращения: 05.04.2023).Hughes, C., Fidopiastis, C., Stanney, K., Bailey, P., Ruiz, E. (2020). The psychometrics of cybersickness in augmented reality. Frontiers in Virtual Reality, vol. 1, ID: 602954. DOI: 10.3389/frvir.2020.602954 (accessed: 05.04.2023).Somanath G., Kurz D. HDR environment map estimation for real-time augmented reality [Электронный ресурс] // IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). USA: Nashville, TN, 2021. Pp. 11293–11301. DOI: 10.1109/CVPR46437.2021.01114 (дата обращения: 05.04.2023).Somanath, G., Kurz, D. (2021). HDR environment map estimation for real-time augmented reality. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, pp. 11293–11301. DOI: 10.1109/CVPR46437.2021.01114 (accessed: 05.04.2023).Zollmann S. Visualization techniques in augmented reality: A taxonomy, methods and patterns / S. Zollmann, T. Langlotz, R. Grasset, W.H. Lo, S. Mori, H. Regenbrecht // IEEE Transactions on Visualization and Computer Graphics, 2021. Vol. 27, no. 9. Pp. 3808–3825. DOI: 10.1109/TVCG.2020.2986247Zollmann, S., Langlotz, T., Grasset, R., Lo, W.H., Mori, S., Regenbrecht, H. (2021). Visualization techniques in augmented reality: A taxonomy, methods and patterns. In: IEEE Transactions on Visualization and Computer Graphics, vol. 27, no. 9, pp. 3808–3825. DOI: 10.1109/TVCG.2020.2986247Kronander J. Photorealistic rendering of mixed reality scenes / J. Kronander, F. Banterle, A. Gardner, E. Miandji, J. Unger // Computer Graphics Forum. 2015. Vol. 34, iss. 2. Pp. 643–665. DOI: 10.1111/cgf.12591Kronander, J., Banterle, F., Gardner, A., Miandji, E., Unger, J. (2015). Photorealistic rendering of mixed reality scenes. Computer Graphics Forum, vol. 34, issue 2, pp. 643–665. DOI: 10.1111/cgf.12591Debevec P. A single-shot light probe / P. Debevec, P. Graham, J. Busch, M. Bolas [Электронный ресурс] // SIGGRAPH '12: Special Interest Group on Computer Graphics and Interactive Techniques Conference. California, Los Angeles, 2012. Article No.: 10. Pp. 1–19. DOI: 10.1145/2343045.2343058 (дата обращения: 05.04.2023).Debevec, P., Graham, P., Busch, J., Bolas, M. (2012). A single-shot light probe. In SIGGRAPH '12: Special Interest Group on Computer Graphics and Interactive Techniques Conference, Los Angeles California, Article No.: 10, pp. 1–19. DOI: 10.1145/2343045.2343058 (accessed: 05.04.2023).Unger J. Capturing and rendering with incident light fields / J. Unger, A. Wenger, T. Hawkins, A. Gardner, P. Debevec // 14th Eurographics Symposium on Rendering, 2003. Pp. 141–149. DOI: 10.2312/EGWR/EGWR03/141-149Unger, J., Wenger, A., Hawkins, T., Gardner, A., Debevec, P. (2003). Capturing and rendering with incident light fields. In: 14th Eurographics Symposium on Rendering, pp. 141–149. DOI: 10.2312/EGWR/EGWR03/141-149Alhakamy A., Tuceryan M. CubeMap360: Interactive global illumination for augmented reality in dynamic environment // Proceedings of IEEE SoutheastCon. USA, Huntsville, AL, 2019. Pp. 1–8. DOI: 10.1109/SoutheastCon42311.2019.9020588Alhakamy, A., Tuceryan, M. (2019). CubeMap360: Interactive global illumination for augmented reality in dynamic environment. In: Proceedings of IEEE SoutheastCon, Huntsville, AL, USA, pp. 1–8. DOI: 10.1109/SoutheastCon42311.2019.9020588Knorr S., Kurz D. Real-time illumination estimation from faces for coherent rendering // 2014 IEEE International Symposium on Mixed and Augmented Reality (ISMAR). Germany, Munich, 2014. Pp. 349–350. DOI: 10.1109/ISMAR.2014.6948483Knorr, S., Kurz, D. (2014). Real-time illumination estimation from faces for coherent rendering. In: 2014 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), Munich, Germany, pp. 349–350. DOI: 10.1109/ISMAR.2014.6948483Karsch K., Sunkavalli K., Hadap S. и др. Automatic scene inference for 3D object compositing // ACM Transactions on Graphics. 2014. Vol. 33, no. 3. Pp. 1–15. DOI: 10.1145/2602146Karsch, K., Sunkavalli, K., Hadap, S., et al. (2014). Automatic scene inference for 3D object compositing. ACM Transactions on Graphics, vol. 33, no. 3, pp. 1–15. DOI: 10.1145/2602146Tsunezaki S. Reproducing material appearance of real objects using mobile augmented reality / S. Tsunezaki, R. Nomura, T. Komuro, S. Yamamoto, N. Tsumura // 2018 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct). Germany, Munich, 2018. Pp. 196–197. DOI: 10.1109/ISMAR-Adjunct.2018.00065Tsunezaki, S., Nomura, R., Komuro, T., Yamamoto, S., Tsumura, N. (2018). Reproducing material appearance of real objects using mobile augmented reality. In: 2018 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), Munich, Germany, pp. 196–197. DOI: 10.1109/ISMAR-Adjunct.2018.00065Reinhard E. Real-time color blending of rendered and captured video / E. Reinhard, A.O. Akyüz, M. Colbert, C. Hughes, M. Oconnor [Электронный ресурс] // Proceedings Interservice/Industry Training, Simulation and Education Conference (I/ITSEC). Orlando, Amerika Birleşik Devletleri, 2004. P. 15021. URL: http://www.ceng.metu.edu.tr/~akyuz/files/blend.pdf (дата обращения: 05.04.2023).Reinhard, E., Akyuz, A.O., Colbert, M., Hughes, C., O’Сonnor, M. (2004). Real-time color blending of rendered and captured video. In: Proceedings Interservice/Industry Training, Simulation and Education Conference (I/ITSEC), Orlando, Amerika Birleşik Devletleri, p. 15021. Available at: http://www.ceng.metu.edu.tr/~akyuz/files/blend.pdf (accessed: 05.04.2023).Chen W.-S., Huang M.-L., Wang C.-M. Optimizing color transfer using color similarity measurement // 2016 IEEE/ACIS 15th International Conference on Computer and Information Science (ICIS), 2016. Pp. 1–6. DOI: 10.1109/ICIS.2016.7550799Chen, W.-S., Huang, M.-L., Wang, C.-M. (2016). Optimizing color transfer using color similarity measurement. In: 2016 IEEE/ACIS 15th International Conference on Computer and Information Science (ICIS), pp. 1–6. DOI: 10.1109/ICIS.2016.7550799Chang Y., Saito S., Nakajima M. Example-Based color transformation of image and video using basic color categories // IEEE Transactions on Image Processing, 2007. Vol. 16, no. 2. Pp. 329–336. DOI: 10.1109/tip.2006.888347Chang, Y., Saito, S., Nakajima, M. (2007). Example-Based color transformation of image and video using basic color categories. In: IEEE Transactions on Image Processing, vol. 16, no. 2, pp. 329–336. DOI: 10.1109/tip.2006.888347Xiao X., Ma L. Gradient-Preserving color transfer // Computer Graphics Forum. 2009. Vol. 28, iss. 7. Pp. 1879–1886. DOI: 10.1111/j.1467-8659.2009.01566.xXiao, X., Ma, L. (2009). Gradient Preserving color transfer. Computer Graphics Forum, vol. 28, issue 7, pp. 1879–1886. DOI: 10.1111/j.1467-8659.2009.01566.xOskam T. Fast and stable color balancing for images and augmented reality / T. Oskam, A. Hornung, R.W. Sumner, M. Gross // 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission (3DIMPVT). Zurich, Switzerland, 13–15 October 2012. Pp. 49–56. DOI: 10.1109/3DIMPVT.2012.36Oskam, T., Hornung, A., Sumner, R.W., Gross, M. (2012). Fast and stable color balancing for images and augmented reality. In: 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission (3DIMPVT), Zurich, Switzerland, October 13–15, pp. 49–56. DOI: 10.1109/3DIMPVT.2012.36Knecht M. Adaptive camera-based color mapping for mixed-reality applications / M. Knecht, C. Traxler, W. Purgathofer, M. Wimmer // 2011 10th IEEE International Symposium on Mixed and Augmented Reality (ISMAR 2011). Switzerland, Basel, 2011. Pp. 165–168. DOI: 10.1109/ISMAR.2011.6092382Knecht, M., Traxler, C., Purgathofer, W., Wimmer, M. (2011). Adaptive CameraBased Color Mapping For Mixed-Reality Applications. In: 2011 10th IEEE International Symposium on Mixed and Augmented Reality (ISMAR 2011), Basel, Switzerland, pp. 165–168. DOI: 10.1109/ISMAR.2011.6092382Einabadi F., Guillemaut J., Hilton A. Deep neural models for illumination estimation and relighting: A survey // Computer Graphics Forum. 2021. Vol. 40, iss. 6. Pp. 315–331. DOI: 10.1111/cgf.14283Einabadi, F., Guillemaut, J., Hilton, A. (2021). Deep neural models for illumination estimation and relighting: A survey. Computer Graphics Forum, vol. 40, issue 6, pp. 315–331. DOI: 10.1111/cgf.14283Gardner M., Sunkavalli K., Yumer E. и др. Learning to predict indoor illumination from a single image // ACM Transactions on Graphics. 2017. Vol. 36, iss. 6. Article No.: 176. Pp. 1–14. DOI: 10.1145/3130800.3130891Gardner, M., Sunkavalli, K., Yumer, E., et al. (2017). Learning to predict indoor illumination from a single image. ACM Transactions on Graphics, vol. 36, issue 6, Article No.: 176, pp. 1–14. DOI: 10.1145/3130800.3130891Song S., Funkhouser T. Neural illumination: Lighting prediction for indoor environments [Электронный ресурс] // Proceedings 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. Pp. 6918–6926. DOI: 10.48550/arXiv.1906.07370 (дата обращения: 05.04.2023).Song, S., Funkhouser, T. (2019). Neural illumination: Lighting prediction for indoor environments. In: Proceedings 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6918–6926. DOI: 10.48550/arXiv.1906.07370 (accessed: 05.04.2023).Cheng D. Learning scene illumination by pairwise photos from rear and front mobile cameras / D. Cheng, J. Shi, Y. Chen, X. Deng, X. Zhang // Computer Graphics Forum. 2018. Vol. 37, iss. 7. Pp. 213–221. DOI: 10.1111/cgf.13561Cheng, D., Shi, J., Chen, Y., Deng, X., Zhang, X. (2018). Learning scene illumination by pairwise photos from rear and front mobile cameras. Computer Graphics Forum, vol. 37, issue 7, pp. 213–221. DOI: 10.1111/cgf.13561Hold-Geoffroy Y. Deep outdoor illumination estimation / Y. Hold-Geoffroy, K. Sunkavalli, S. Hadap, E. Gambaretto, J.-F. Lalonde [Электронный ресурс] // Proceedings 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). USA, Honolulu, HI, 2017. Pp. 2373–2382. DOI: 10.1109/CVPR.2017.255 (дата обращения: 05.04.2023).Hold-Geoffroy, Y., Sunkavalli, K., Hadap, S., Gambaretto, E., Lalonde, J. (2017). Deep outdoor illumination estimation. In: Proceedings 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 2373–2382. DOI: 10.1109/CVPR.2017.255 (accessed: 05.04.2023).Zhao Y., Guo T. PointAR: Effcient lighting estimation for mobile augmented reality // 16th European Conference on Computer Vision (ECCV'20), 2020. Pp. 678–693. DOI: 10.48550/arXiv.2004.00006Zhao, Y., Guo, T. (2020). Point AR: Effcient lighting estimation for mobile augmented reality. In: 16th European Conference on Computer Vision (ECCV'20), pp. 678–693. DOI: 10.48550/arXiv.2004.00006Garon M. Fast spatially-varying in-door lighting estimation / M. Garon, K. Sunkavalli, S. Hadap, N. Carr, J. Lalonde [Электронный ресурс] // Proceedings IEEE Conference on Computer Vision and Pattern Recognition, 2019. Pp. 6908–6917. DOI: 10.48550/arXiv.1906.03799 (дата обращения: 05.04.2023).Garon, M., Sunkavalli, K., Hadap, S., Carr, N., Lalonde, J. (2019). Fast spatiallyvarying in-door lighting estimation. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 6908–6917. DOI: 10.48550/arXiv.1906.03799 (accessed: 05.04.2023).LeGendre C., Ma W., Fyffe G. и др. Deep-light: Learning illumination for unconstrained mobile mixed reality [Электронный ресурс] // Proceedings IEEE Conference on Computer Vision and Pattern Recognition, 2019. Pp. 5918–5928. DOI: 10.48550/arXiv.1904.01175 (дата обращения: 05.04.2023).LeGendre, C., Ma, W., Fyffe, G., et al. (2019). DeepLight: Learning illumination for unconstrained mobile mixed reality. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 5918–5928. DOI: 10.48550/arXiv.1904.01175 (accessed: 05.04.2023).Srinivasan P. Lighthouse: Predicting lighting volumes for spatially-coherent illumination / P. Srinivasan, B. Mildenhall, M. Tancik, J. Barron, R. Tucker, N. Snavely [Электронный ресурс] // Proceedings IEEE Conference on Computer Vision and Pattern Recognition, 2020. Pp. 8080–8089. DOI: 10.48550/arXiv.2003.08367 (дата обращения: 05.04.2023).Srinivasan, P., Mildenhall, B., Tan‐ cik, M., Barron, J., Tucker, R., Snavely, N. (2020). Lighthouse: Predicting lighting volumes for spatially-coherent illumination. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, pp. 8080–8089. DOI: 10.48550/arXiv.2003.08367 (accessed: 05.04.2023).Tewari A., Fried O., Thies J. и др. State of the art on neural rendering // Computer Graphics Forum. 2020. Vol. 39, iss. 2. Pp. 701–727. DOI: 10.1111/cgf.14022Tewari, A., Fried, O., Thies, J., et al. (2020). State of the art on neural rendering. Computer Graphics Forum, vol. 39, issue 2, pp. 701–727. DOI: 10.1111/cgf.14022Goodfellow I., Pouget-Abadie J., Mirza M. и др. Generative adversarial nets // Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014. Vol. 2. Pp. 2672–2680. DOI: 10.5555/2969033.2969125Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al. (2014). Generative adversarial nets. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, vol. 2, pp. 2672–2680. DOI: 10.5555/2969033.2969125Karras T., Laine S., Aila T. A stylebased generator architecture for generative adversarial networks [Электронный ресурс] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). USA, Long Beach, CA, 2019. Pp. 4396–4405. DOI: 10.1109/CVPR.2019.00453 (дата обращения: 05.04.2023).Karras, T., Laine, S., Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp. 4396–4405. DOI: 10.1109/CVPR.2019.00453 (accessed: 05.04.2023).Bi S. Deep CG2Real: Synthetic-to-real translation via image disentanglement / S. Bi, K. Sunkavalli, F. Perazzi, E. Shechtman, V. Kim, R. Ramamoorthi // 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019. Pp. 2730–2739. DOI: 10.1109/ICCV.2019.00282Bi, S., Sunkavalli, K., Perazzi, F., Shechtman, E., Kim, V., Ramamoorthi, R. (2019). Deep CG2Real: Synthetic-to-real translation via image disentanglement. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 2730–2739. DOI: 10.1109/ICCV.2019.00282Xu Z. Deep view synthesis from sparse photometric images / Z. Xu, S. Bi, K. Sunkavalli, S. Hadap, H. Su, R. Ramamoorthi [Электронный ресурс] // ACM Transactions on Graphics. 2019. Vol. 38, iss. 412. Article No.: 76. Pp. 1–13. DOI: 10.1145/3306346.3323007 (дата обращения: 05.04.2023).Xu, Z., Bi, S., Sunkavalli, K., Hadap, S., Su, H., Ramamoorthi, R. (2019). Deep view synthesis from sparse photometric images. ACM Transactions on Graphics, vol. 38, issue 412, Article No.: 76, pp. 1–13. DOI: 10.1145/3306346.3323007 (accessed: 05.04.2023).Park T. Semantic image synthesis with spatially-adaptive normalization / T. Park, M. Liu, T. Wang, J. Zhu [Электронный ресурс] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019. 19 p. DOI: 10.48550/arXiv.1903.07291 (дата обращения: 05.04.2023).Park, T., Liu, M., Wang, T., Zhu, J. (2019). Semantic image synthesis with spatiallyadaptive normalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 19 p. DOI: 10.48550/arXiv.1903.07291 (accessed: 05.04.2023).Li Z. Inverse rendering for complex indoor scenes: Shape, spatially-varying lighting and SVBRDF from a single image / Z. Li, M. Shafiei, R. Ramamoorthi, K. Sunkavalli, M. Chandraker [Электронный ресурс] // Proceedings IEEE Conference on Computer Vision and Pattern Recognition, 2020. Pp. 2475–2484. DOI: 10.48550/arXiv.1905.02722 (дата обращения: 05.04.2023).Li, Z., Shafiei, M., Ramamoorthi, R., Sunkavalli, K., Chandraker, M. (2020). Inverse rendering for complex indoor scenes: Shape, spatially-varying lighting and SVBRDF from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2475–2484. DOI: 10.48550/arXiv.1905.02722 (accessed: 05.04.2023).Zhan F., Yu Y., Wu R. и др. Bi-level feature alignment for semantic image translation and manipulation [Электронный ресурс] // Proceedings IEEE Conference on Computer Vision and Pattern Recognition, 2022. 18 p. DOI: 10.48550/arXiv.2107.03021 (дата обращения: 05.04.2023).Zhan, F., Yu, Y., Wu, R., et al. (2022). Bi-level feature alignment for semantic image translation and manipulation. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, 18 p. DOI: 10.48550/arXiv.2107.03021 (accessed: 05.04.2023).Ghasemi Y. Deep learning-based object detection in augmented reality: A systematic review / Y. Ghasemi, H. Jeong, S. Choi, J. Lee, K. Park [Электронный ресурс] // Computers in Industry. 2022. Vol. 139. ID: 103661. DOI: 10.1016/j.compind.2022.103661 (дата обращения: 05.04.2023).Ghasemi, Y., Jeong, H., Choi, S., Lee, J., Park, K. (2022). Deep learning-based object detection in augmented reality: A systematic review. Computers in Industry, vol. 139, ID: 103661. DOI: 10.1016/j.compind.2022.103661 (accessed: 05.04.2023).

The authors declare that there are no conflicts of interest present.