<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD with OASIS Tables with MathML3 v1.4 20241031//EN" "https://jats.nlm.nih.gov/archiving/1.4/JATS-archive-oasis-article1-4-mathml3.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" dtd-version="1.4" article-type="research-article" xml:lang="en"><front><journal-meta><journal-title-group><journal-title xml:lang="ru">Математическая физика и компьютерное моделирование</journal-title></journal-title-group><issn publication-format="print">2587-6325</issn><issn publication-format="electronic">2587-6902</issn></journal-meta><article-meta><article-id pub-id-type="doi">10.15688/mpcm.jvolsu.2023.4.3</article-id><article-categories><subj-group><subject>Other</subject></subj-group></article-categories><title-group><article-title xml:lang="ru">Построение 3D модели объекта по набору его изображений при помощи нейронной сети на базе алгоритма</article-title><trans-title-group xml:lang="en"><trans-title>Building a 3D-Model of an Object from a Set of Its Images Using a Neural Network Based on the NeRF Algorithm</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><name-alternatives><name xml:lang="ru"><surname>Дряба</surname><given-names>Александр Юрьевич</given-names></name><name xml:lang="en"><surname>Dryaba</surname><given-names>Alexander Yu.</given-names></name></name-alternatives><xref ref-type="aff" rid="aff1"/><email>casha.dryaba@mail.ru</email><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0002-9587-9179</contrib-id></contrib><aff-alternatives id="aff1"><aff xml:lang="en"><institution>Volgograd State University(Volgograd, Russian Federation)</institution></aff><aff xml:lang="ru"><institution>Волгоградский государственный университет(г. Волгоград, Российская Федерация)</institution></aff></aff-alternatives></contrib-group><pub-date pub-type="epub" iso-8601-date="2023-12-10"><day>10</day><month>12</month><year>2023</year></pub-date><volume>26</volume><issue>4</issue><fpage>31</fpage><lpage>42</lpage><history><date date-type="received" iso-8601-date="2023-07-20"><day>20</day><month>07</month><year>2023</year></date><date date-type="accepted" iso-8601-date="2023-10-01"><day>01</day><month>10</month><year>2023</year></date></history><permissions><license xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:title="CC BY 4.0"><ali:license_ref>https://creativecommons.org/licenses/by/4.0/</ali:license_ref><license-p xml:lang="ru">CC BY 4.0</license-p></license></permissions><abstract xml:lang="ru"><p>В работе представлены способы реконструирования трехмерных моделей объектов по набору плоских изображений с использованием алгоритма NeRF для получения представления объемной сцены в виде весов многослойного перцептрона. Для каждого способа прилагается оценка затрачиваемого времени. Исходя из полученных данных можно сделать вывод о возможности распознавания форм объектов из естественной обстановки в пределах 5–10 минут, при условии переноса шага обучения нейронной сети на сторону сервера.</p></abstract><abstract xml:lang="en" abstract-type="summary"><p>The work was conducted as part of the development of a computer vision system for analyzing the environment, which could be utilized, for instance, by an autonomous mobile robot. This system involves using a camera to gather information about the surrounding environment. The paper presents methods for reconstructing three-dimensional models of objects solely from a set of 2D-images, using the NeRF algorithm to obtain a representation of a three-dimensional scene in the form of weights of a multilayer perceptron. Each method includes an estimate of the algorithm’s time consumption. Based on the data obtained, it was concluded that it is feasible to recognize the shapes of objects from a natural environment within 5–10 minutes, provided that the neural network training step is transferred to the server side.</p></abstract><kwd-group xml:lang="ru"><kwd>3D реконструкция</kwd><kwd>NeRF</kwd><kwd>карта глубин</kwd><kwd>MLP, объемный рендеринг</kwd></kwd-group><kwd-group xml:lang="en"><kwd>3D-reconstruction</kwd><kwd>NeRF</kwd><kwd>depth map</kwd><kwd>MLP, volume rendering</kwd></kwd-group></article-meta></front><back><ref-list><ref id="ref1"><mixed-citation publication-type="other" xml:lang="ru">Гадасин, Д. В. Трехмерная реконструкция объекта по одному изображению с использованием глубоких сверточных нейронных сетей / Д. В. Гадасин, А. В. Шведов, И. А. Кузин // T-Comm: телекоммуникации и транспорт. — 2022. — Т. 16, № 7. — C. 29–34. — DOI: http://dx.doi.org/10.36724/2072-8735-2022-16-7-29-35</mixed-citation></ref><ref id="ref2"><mixed-citation publication-type="other" xml:lang="ru">Камеры глубины — тихая революция (когда роботы будут видеть). Ч. 1. — Электрон. текстовые дан. — Режим доступа: https://habr.com/ru/articles/457524. — Загл. с экрана.</mixed-citation></ref><ref id="ref3"><mixed-citation publication-type="other" xml:lang="ru">Клячин, А. А. Алгоритм восстановления поверхности объекта по его изображению / А. А. Клячин, В. А. Клячин // Математическая физика и компьютерное моделирование. — 2021. — Т. 24, № 1. — C. 16–24. — DOI: https://doi.org/10.15688/mpcm.jvolsu.2021.1.2</mixed-citation></ref><ref id="ref4"><mixed-citation publication-type="other" xml:lang="ru">Клячин, А. А. Теоремы существования и единственности решения обратных задач проективной геометрии для 3D реконструкции по фотоснимкам / А. А. Клячин, В. А. Клячин // Чебышевский сборник. — 2020. — Т. 21, № 4. — C. 117–128. — DOI: https://doi.org/10.22405/2226-8383-2020-21-4-117-128</mixed-citation></ref><ref id="ref5"><mixed-citation publication-type="other" xml:lang="ru">Клячин, В. А. Алгоритм 3D реконструкции поверхности вращения по ее проекции / В. А. Клячин, Е. Г. Григорьева // Сибирский журнал индустриальной математики. — 2020. — Т. 23, № 1. — C. 84–92. — DOI: https://doi.org/10.33048/SIBJIM.2020.23.108</mixed-citation></ref><ref id="ref6"><mixed-citation publication-type="other" xml:lang="ru">Клячин, В. А. Теоремы единственности восстановления прообраза при вырожденном преобразовании / В. А. Клячин, Е. Г. Григорьева // Математическая физика и компьютерное моделирование. — 2022. — Т. 25, № 2. — C. 17–22. — DOI: https://doi.org/10.15688/mpcm.jvolsu.2022.2.2</mixed-citation></ref><ref id="ref7"><mixed-citation publication-type="other" xml:lang="ru">Реализация архитектуры Tiny NeRF. — Электрон. текстовые дан. — Режим доступа: https://github.com/bmild/nerf/blob/master/tiny_nerf.ipynb. — Загл. с экрана.</mixed-citation></ref><ref id="ref8"><mixed-citation publication-type="other" xml:lang="ru">Few-Shot Single-View 3D Reconstruction with Memory Prior Contrastive Network / Z. Xing, Y. J. Chen, Z. X. Ling, X. D. Zhou, Y. Xiang // ECCV 2022: Computer Vision — ECCV 2022. — 2022. — № 1. — P. 55–70. — DOI: https://doi.org/10.1007/978-3-031-19769-7_4</mixed-citation></ref><ref id="ref9"><mixed-citation publication-type="other" xml:lang="ru">Jackson, A. S. Learning Deep Architectures for AI / A. S. Jackson // Foundations. — 2009. — № 2. — P. 1–55. — DOI: http://dx.doi.org/10.1561/2200000006</mixed-citation></ref><ref id="ref10"><mixed-citation publication-type="other" xml:lang="ru">Large Pose 3D Face Reconstruction from a Single Image Via Direct Volumetric CNN Regression / A. S. Jackson, A. Bulat, V. Argyriou, G. Tzimiropoulos // 2017 IEEE International Conference on Computer Vision (ICCV). — 2017. — P. 1031–1039. — DOI: http://dx.doi.org/10.1109/ICCV.2017.117</mixed-citation></ref><ref id="ref11"><mixed-citation publication-type="other" xml:lang="ru">Multilayer Perceptron Explained with a Real-Life Example and Python Code: Sentiment Analysis. — Electronic text data. — Mode of access: https://towardsdatascience.com/multilayerperceptron-explained-with-a-real-life-example-and-python-code-sentiment-analysiscb408ee93141. — Title from screen.</mixed-citation></ref><ref id="ref12"><mixed-citation publication-type="other" xml:lang="ru">NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis / B. Mildenhall, P. P. Srinivasan, M. Tancik, J. T. Barron, R. Ramamoorthi, R. Ng // Computer Vision − ECCV 2020. — 2020. — № 12346. — P. 405–421. — DOI: https://doi.org/10.1007/978-3-030-58452-8_24</mixed-citation></ref><ref id="ref13"><mixed-citation publication-type="other" xml:lang="ru">Neural 3D Reconstruction in the Wild / J. M. Sun, X. Chen, Q. Q. Wang, Z. Q. Li, H. Averbuch-Elor, X. W. Zhou, N. Snavely // ACM SIGGRAPH 2022 Conference Proceedings. — NY : Association for Computing Machinery, 2022. — P. 1–9. — DOI: https://doi.org/10.1145/3528233.3530718</mixed-citation></ref><ref id="ref14"><mixed-citation publication-type="other" xml:lang="ru">RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation / T. Anciukevicius, Z. X. Xu, M. Fisher, P. Henderson, H. Bilen, N. J. Mitra, P. Guerrero // CVPR 2023: IEEE Conference on Computer Vision and Pattern Recognition. — 2023. — P. 12608–12618. — DOI: https://doi.org/10.1109/CVPR52729.2023.01213</mixed-citation></ref><ref id="ref15"><mixed-citation publication-type="other" xml:lang="en">Gadasin D.V., Shvedov A.V., Kuzin I.A. Trekhmernaya rekonstruktsiya obyekta po odnomu izobrazheniyu s ispolzovaniem glubokikh svyortochnykh neyronnykh setey [ThreeDimentional Reconstruction of an Object From a Single Image Using Deep Convolutional Neural Networks]. T-Comm: telekommunikatsii i transport, 2022, vol. 16, no. 7, pp. 29-34. DOI: http://dx.doi.org/10.36724/2072-8735-2022-16-7-29-35</mixed-citation></ref><ref id="ref16"><mixed-citation publication-type="other" xml:lang="en">Kamery glubiny — tikhaya revolyutsiya (kogda roboty budut videt). Ch. 1 [Depth Cameras − a Silent Revolution (When Robots Could See). Part 1]. URL: https://habr.com/ru/articles/457524</mixed-citation></ref><ref id="ref17"><mixed-citation publication-type="other" xml:lang="en">Klyachin A.A., Klyachin V.A. Algoritm vosstanovleniya poverkhnosti obyekta po ego izobrazheniyu [Algorithm for Restoring the Surface of an Object from its Image]. Matematicheskaya fizika i kompyuternoe modelirovanie [Mathematical Physics and Computer Simulation], 2021, vol. 24, no. 1, pp. 16-24. DOI: https://doi.org/10.15688/mpcm.jvolsu.2021.1.2</mixed-citation></ref><ref id="ref18"><mixed-citation publication-type="other" xml:lang="en">Klyachin A.A., Klyachin V.A. Teoremy sushchestvovaniya i edinstvennosti resheniya obratnykh zadach proektivnoy geometrii dlya 3D rekonstruktsii po fotosnimkam [Existence and Uniqueness Theorems for Solutions of Inverse Problems of Projective Geometry for 3D Reconstruction from Photographs]. Chebyshevskiy sbornik, 2020, vol. 21, no. 4, pp. 117-128. DOI: https://doi.org/10.22405/2226-8383-2020-21-4-117-128</mixed-citation></ref><ref id="ref19"><mixed-citation publication-type="other" xml:lang="en">Klyachin V.A., Grigoryeva E.G. Algoritm 3D rekonstruktsii poverkhnosti vrashcheniya po eyo proektsii [A 3D Reconstruction Algorithm of a Surface of Revolution from its Projection]. Sibirskiy zhurnal industrialnoy matematiki [Journal of Applied and Industrial Mathematics], 2020, vol. 23, no. 1, pp. 84-92. DOI: https://doi.org/10.33048/SIBJIM.2020.23.108</mixed-citation></ref><ref id="ref20"><mixed-citation publication-type="other" xml:lang="en">Klyachin V.A., Grigoryeva E.G. Teoremy edinstvennosti vosstanovleniya proobraza pri vyrozhdennom preobrazovanii [Uniqueness Theorem of Reconstruction of Preimage by its Image under Degenerate Mapping]. Matematicheskaya fizika i kompyuternoe modelirovanie [Mathematical Physics and Computer Simulation], 2022, vol. 25, no. 2, pp. 17-22. DOI: https://doi.org/10.15688/mpcm.jvolsu.2022.2.2</mixed-citation></ref><ref id="ref21"><mixed-citation publication-type="other" xml:lang="en">Realizatsiya arkhitektury Tiny NeRF [Tiny NeRF Implementation]. URL: https://github.com/bmild/nerf/blob/master/tiny_nerf.ipynb</mixed-citation></ref><ref id="ref22"><mixed-citation publication-type="other" xml:lang="en">Xing Z., Chen Y.J., Ling Z.X., Zhou X.D., Xiang Y. Few-Shot Single-View 3D Reconstruction with Memory Prior Contrastive Network. ECCV 2022: Computer Vision — ECCV 2022, 2022, no. 1, pp. 55-70. DOI: https://doi.org/10.1007/978-3-031-19769-7_4</mixed-citation></ref><ref id="ref23"><mixed-citation publication-type="other" xml:lang="en">Jackson A.S. Learning Deep Architectures for AI. Foundations, 2009, no. 2, pp. 1-55. DOI: http://dx.doi.org/10.1561/2200000006</mixed-citation></ref><ref id="ref24"><mixed-citation publication-type="other" xml:lang="en">Jackson A.S., Bulat A., Argyriou V., Tzimiropoulos G. Large Pose 3D Face Reconstruction From a Single Image Via Direct Volumetric CNN Regression. 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1031-1039. DOI: http://dx.doi.org/10.1109/ICCV.2017.117</mixed-citation></ref><ref id="ref25"><mixed-citation publication-type="other" xml:lang="en">Multilayer Perceptron Explained with a Real-Life Example and Python Code: Sentiment Analysis. URL: https://towardsdatascience.com/multilayer-perceptron-explainedwith-a-real-life-example-and-python-code-sentiment-analysis-cb408ee93141</mixed-citation></ref><ref id="ref26"><mixed-citation publication-type="other" xml:lang="en">Mildenhall B., Srinivasan P.P., Tancik M., Barron J.T., Ramamoorthi R., Ng R. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. Computer Vision − ECCV 2020, 2020, no. 12346, pp. 405-421. DOI: https://doi.org/10.1007/978-3-030-58452-8_24</mixed-citation></ref><ref id="ref27"><mixed-citation publication-type="other" xml:lang="en">Sun J.M., Chen X., Wang Q.Q., Li Z.Q., Averbuch-Elor H., Zhou X.W., Snavely N. Neural 3D Reconstruction in the Wild. ACM SIGGRAPH 2022 Conference Proceedings. NY, Association for Computing Machinery, 2022, pp. 1-9. DOI: https://doi.org/10.1145/3528233.3530718</mixed-citation></ref><ref id="ref28"><mixed-citation publication-type="other" xml:lang="en">Anciukevicius T., Xu Z.X., Fisher M., Henderson P., Bilen H., Mitra N.J., Guerrero P. RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation. CVPR 2023: IEEE Conference on Computer Vision and Pattern Recognition, 2023, pp. 12608-12618. DOI: https://doi.org/10.1109/CVPR52729.2023.01213</mixed-citation></ref></ref-list></back></article>
