<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">ntv</journal-id><journal-title-group><journal-title xml:lang="ru">Научно-технический вестник информационных технологий, механики и оптики</journal-title><trans-title-group xml:lang="en"><trans-title>Scientific and Technical Journal of Information Technologies, Mechanics and Optics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2226-1494</issn><issn pub-type="epub">2500-0373</issn><publisher><publisher-name>Университет ИТМО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17586/2226-1494-2025-25-2-321-327</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-452</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>КОМПЬЮТЕРНЫЕ СИСТЕМЫ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>COMPUTER SCIENCE</subject></subj-group></article-categories><title-group><article-title>Метод увеличения разрешения изображения с использованием референсных изображений на основе диффузионной модели</article-title><trans-title-group xml:lang="en"><trans-title>Reference-based diffusion model for super-resolution</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-8135-1723</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Денисов</surname><given-names>А. К.</given-names></name><name name-style="western" xml:lang="en"><surname>Denisov</surname><given-names>A. K.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Денисов Алексей Константинович — ассистент.</p><p>Санкт-Петербург, 197101, sc 57210698353</p></bio><bio xml:lang="en"><p>Aleksei K. Denisov — Assistant.</p><p>Saint Petersburg, 197101, sc 57210698353</p></bio><email xlink:type="simple">denisov@itmo.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-4163-9743</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Быковский</surname><given-names>С. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Bykovskii</surname><given-names>S. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Быковский Сергей Вячеславович — кандидат технических наук, доцент.</p><p>Санкт-Петербург, 197101, sc 57216469537</p></bio><bio xml:lang="en"><p>Sergei V. Bykovskii — PhD, Associate Professor.</p><p>Saint Petersburg, 197101, sc 57216469537</p></bio><email xlink:type="simple">sergei_bykovskii@itmo.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-9326-0837</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Кустарев</surname><given-names>П. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Kustarev</surname><given-names>P. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Кустарев Павел Валерьевич — кандидат технических наук, декан.</p><p>Санкт-Петербург, 197101, sc 35317916600</p></bio><bio xml:lang="en"><p>Pavel V. Kustarev — PhD, Dean.</p><p>Saint Petersburg, 197101, sc 35317916600</p></bio><email xlink:type="simple">kustarev@itmo.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Университет ИТМО</institution><country>Россия</country></aff><aff xml:lang="en"><institution>ITMO University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>24</day><month>04</month><year>2025</year></pub-date><volume>25</volume><issue>2</issue><fpage>321</fpage><lpage>327</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Денисов А.К., Быковский С.В., Кустарев П.В., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Денисов А.К., Быковский С.В., Кустарев П.В.</copyright-holder><copyright-holder xml:lang="en">Denisov A.K., Bykovskii S.V., Kustarev P.V.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://ntv.elpub.ru/jour/article/view/452">https://ntv.elpub.ru/jour/article/view/452</self-uri><abstract><sec><title>Введение</title><p>Введение. В настоящий момент активно развиваются различные методы восстановления изображений на основе методов глубокого машинного обучения. С помощью таких методов решаются задачи восстановления утраченных областей, подавления шумов и увеличения разрешения изображений. В задаче увеличения разрешения важную роль играют методы, основанные на применении референсных изображений, позволяющих восстановить недостающую информацию на основном изображении. Такие методы реализуются с использованием сверточных нейронных сетей, широко востребованных в задачах компьютерного зрения. В применяемых в настоящее время методах область изображения, не представленная на референсном изображении, часто отличается худшим качеством по сравнению с остальным изображением, что заметно визуально. Наряду со сверточными нейронными сетями в задачах восстановления изображений активно применяются диффузионные модели, позволяющие генерировать изображения с высоким качеством и четкостью, однако их недостатком часто бывает несоответствие сгенерированных деталей реальным. В работе обсуждается проблема улучшения качества восстановления изображений на основе применения референсных изображений с использованием диффузионной модели.</p></sec><sec><title>Метод</title><p>Метод. Для получения хорошего конечного результата предложена гибридная архитектура нейронной сети диффузионной модели, состоящая из трех основных блоков: базового модуля диффузионной модели, модуля использования референсной информации и модуля слияния. Обучение предложенной гибридной модели, а также сравниваемой с ней сверточной нейронной сети, использующей референсные изображения, и диффузионной моделью выполнено с использованием набора данных Large-Scale Multi-Reference Dataset (LMR).</p></sec><sec><title>Основные результаты</title><p>Основные результаты. По результатам тестирования обученных моделей на тестовой выборке набора данных LMR проведено качественное (визуальное) и количественное сравнение работы трех моделей. Гибридная модель продемонстрировала более высокое качество, четкость и однородность изображения в сравнении со сверточной нейронной сетью с использованием референсных изображений и лучшее восстановление реальных деталей по сравнению с диффузионной моделью. Количественные оценки подтвердили, что гибридная модель также показала более высокие результаты по сравнению с остальными моделями. Обсуждение. Результаты работы могут быть использованы для увеличения разрешения любых изображений с использованием референсной информации.</p></sec></abstract><trans-abstract xml:lang="en"><p>This article is devoted to digital image processing algorithms, namely, super-resolution task. Currently, various methods of image restoration based on deep learning are actively developing. These methods are used to solve image restoration problems, such as inpainting, denoising, and super-resolution. One important class of super-resolution methods is reference-based super-resolution that allows restoring the missing information in the main image using reference images. Methods of this class are mainly represented by convolutional neural networks which are widely used in computer vision problems. Despite the significant achievements of existing methods, they have one significant drawback: the image area not represented in the reference image often has worse quality compared to the rest of the image, which is clearly visible to the observer. In addition to convolutional neural networks, diffusion models are actively used in image restoration problems. They are capable of generating images with high quality and diverse fine details but suffer from a lack of fidelity between the generated details and the real ones. The aim of this work is to improve the quality of the reference-based image restoration method using the diffusion model. A hybrid architecture of the diffusion model denoising neural network is proposed consisting of three main blocks: the basic denoising module, the reference-based module, and the fusion module for the final result generation. Three models were trained: a diffusion model, a referencebased convolutional neural network, and a proposed hybrid model. All three models were trained and evaluated on the Large-Scale Multi-Reference Dataset dataset. Based on the results of the trained models testing, a qualitative (visual) and quantitative comparison of the three models was done. The hybrid model demonstrated higher image quality, clarity, and consistency compared to the convolutional neural network using references and better restoration of real details compared to the diffusion model. According to the quantitative evaluation, the hybrid model also showed higher results compared to pure models. The results of this work can be used to increase the resolution of any images using reference information.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>обработка изображений</kwd><kwd>диффузионные модели</kwd><kwd>super-resolution</kwd><kwd>глубокое обучение</kwd><kwd>восстановление изображений</kwd></kwd-group><kwd-group xml:lang="en"><kwd>image processing</kwd><kwd>diffusion models</kwd><kwd>super-resolution</kwd><kwd>deep learning</kwd><kwd>image restoration</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Dong C., Loy C.C., He K., Tang X. Image Super-Resolution using deep convolutional networks // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016. V. 38. N 2. P. 295–307. https://doi.org/10.1109/TPAMI.2015.2439281</mixed-citation><mixed-citation xml:lang="en">Dong C., Loy C.C., He K., Tang X. Image Super-Resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, vol. 38, no. 2, pp. 295–307. https://doi.org/10.1109/TPAMI.2015.2439281</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Kim J., Lee J.K., Lee K.M. Accurate image Super-Resolution using very deep convolutional networks // Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. P. 1646– 1654. https://doi.org/10.1109/CVPR.2016.182</mixed-citation><mixed-citation xml:lang="en">Kim J., Lee J.K., Lee K.M. Accurate image Super-Resolution using very deep convolutional networks. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1646– 1654. https://doi.org/10.1109/CVPR.2016.182</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Lim B., Son S., Kim H., Nah S., Lee K.M. Enhanced deep residual networks for single image Super-Resolution // Proc. of the IEEE Conference on Computer Vision and Pattern Recognition Workshops ( CVPRW). 2017 . P. 1132– 1140 . https://doi.org/10.1109/CVPRW.2017.151</mixed-citation><mixed-citation xml:lang="en">Lim B., Son S., Kim H., Nah S., Lee K.M. Enhanced deep residual networks for single image Super-Resolution. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017, pp. 1132–1140. https://doi.org/10.1109/CVPRW.2017.151</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Ledig C., Theis L., Huszár F., Caballero J., Cunningham A., Acosta A., Aitken A., Tejani A., Totz J., Wang Z., Shi W. Photo-realistic single image Super-Resolution using a generative adversarial network // Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. P. 105–114. https://doi.org/10.1109/10.1109/CVPR.2017.19</mixed-citation><mixed-citation xml:lang="en">Ledig C., Theis L., Huszár F., Caballero J., Cunningham A., Acosta A., Aitken A., Tejani A., Totz J., Wang Z., Shi W. Photo-realistic single image Super-Resolution using a generative adversarial network. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 105–114. https://doi.org/10.1109/10.1109/CVPR.2017.19</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Wang X., Xie L., Dong C., Shan Y. Real-ESRGAN: training real-world blind Super-Resolution with pure synthetic data // Proc. of the IEEE/ CVF International Conference on Computer Vision Workshops (ICCVW). 2021. P. 1905–1914. https://doi.org/10.1109/ICCVW54120.2021.00217</mixed-citation><mixed-citation xml:lang="en">Wang X., Xie L., Dong C., Shan Y. Real-ESRGAN: training real-world blind Super-Resolution with pure synthetic data. Proc. of the IEEE/ CVF International Conference on Computer Vision Workshops (ICCVW), 2021, pp. 1905–1914. https://doi.org/10.1109/ICCVW54120.2021.00217</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang Z., Wang Z., Lin Z., Qi H. Image Super-Resolution by neural texture transfer // Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019. P. 7974–7983. https://doi.org/10.1109/CVPR.2019.00817</mixed-citation><mixed-citation xml:lang="en">Zhang Z., Wang Z., Lin Z., Qi H. Image Super-Resolution by neural texture transfer. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 7974–7983. https://doi.org/10.1109/CVPR.2019.00817</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Jiang Y., Chan K.C.K., Wang X., Loy C.C., Liu Z. Robust Referencebased Super-Resolution via C2-Matching // Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021. P. 2103–2112. https://doi.org/10.1109/CVPR46437.2021.00214</mixed-citation><mixed-citation xml:lang="en">Jiang Y., Chan K.C.K., Wang X., Loy C.C., Liu Z. Robust Referencebased Super-Resolution via C2-Matching. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 2103–2112. https://doi.org/10.1109/CVPR46437.2021.00214</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Cao J., Liang J., Zhang K., Li Y., Zhang Y., Wang W., Van Gool L. Reference-based image Super-Resolution with deformable attention transformer // Lecture Notes in Computer Science. 2022. V. 13678. P. 325–342. https://doi.org/10.1007/978-3-031-19797-0_19</mixed-citation><mixed-citation xml:lang="en">Cao J., Liang J., Zhang K., Li Y., Zhang Y., Wang W., Van Gool L. Reference-based image Super-Resolution with deformable attention transformer. Lecture Notes in Computer Science, 2022, vol. 13678, pp. 325–342. https://doi.org/10.1007/978-3-031-19797-0_19</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang L., Li X., He D., Li F., Ding E., Zhang Z. LMR: a large-scale multi-reference dataset for Reference-based Super-Resolution // Proc. of the IEEE/CVF International Conference on Computer Vision (ICCV). 2023. P. 13072–13081. https://doi.org/10.1109/ICCV51070.2023.01206</mixed-citation><mixed-citation xml:lang="en">Zhang L., Li X., He D., Li F., Ding E., Zhang Z. LMR: a large-scale multi-reference dataset for Reference-based Super-Resolution. Proc. of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 13072–13081. https://doi.org/10.1109/ICCV51070.2023.01206</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Li G., Xing W., Zhao L., Lan Z., Sun J., Zhang Z., Zhang Q., Lin H., Lin Z. Self-Reference image Super-Resolution via pre-trained diffusion large model and window adjustable transformer // Proc. of the 31st ACM International Conference on Multimedia. 2023. P. 7981–7992. https://doi.org/10.1145/3581783.3611866</mixed-citation><mixed-citation xml:lang="en">Li G., Xing W., Zhao L., Lan Z., Sun J., Zhang Z., Zhang Q., Lin H., Lin Z. Self-Reference image Super-Resolution via pre-trained diffusion large model and window adjustable transformer. Proc. of the 31st ACM International Conference on Multimedia, 2023, pp. 7981–7992. https://doi.org/10.1145/3581783.3611866</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Ho J., Jain A., Abbeel P. Denoising diffusion probabilistic models // arXiv. 2020. arXiv:2006.11239. https://doi.org/10.48550/arXiv.2006.11239</mixed-citation><mixed-citation xml:lang="en">Ho J., Jain A., Abbeel P. Denoising diffusion probabilistic models. arXiv, 2020, arXiv:2006.11239. https://doi.org/10.48550/arXiv.2006.11239</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Song J., Meng C., Ermon S. Denoising diffusion implicit models // arXiv. 2020. arXiv:2010.02502. https://doi.org/10.48550/arXiv.2010.02502</mixed-citation><mixed-citation xml:lang="en">Song J., Meng C., Ermon S. Denoising diffusion implicit models. arXiv, 2020, arXiv:2010.02502. https://doi.org/10.48550/arXiv.2010.02502</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Rombach R., Blattmann A., Lorenz D., Esser P., Ommer B. HighResolution image synthesis with latent diffusion models // Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022. P. 10674–10685. https://doi.org/10.1109/CVPR52688.2022.01042</mixed-citation><mixed-citation xml:lang="en">Rombach R., Blattmann A., Lorenz D., Esser P., Ommer B. HighResolution image synthesis with latent diffusion models. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 10674–10685. https://doi.org/10.1109/CVPR52688.2022.01042</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Li H., Yang Y., Chang M., Chen S., Feng H., Xu Z., Li Q., Chen Y. SRDiff: Single Image Super-Resolution with diffusion probabilistic models // Neurocomputing. 2022. V. 479. P. 47–59. https://doi.org/10.1016/j.neucom.2022.01.029</mixed-citation><mixed-citation xml:lang="en">Li H., Yang Y., Chang M., Chen S., Feng H., Xu Z., Li Q., Chen Y. SRDiff: Single Image Super-Resolution with diffusion probabilistic models. Neurocomputing, 2022, vol. 479, pp. 47–59. https://doi.org/10.1016/j.neucom.2022.01.029</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Yu F., Gu J., Li Z., Liu J., Kong X., Wang X., He J., Qiao Y., Dong C. Scaling Up to Excellence: practicing model scaling for photo-realistic image restoration in the wild // Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2024. P. 25669–25680. https://doi.org/10.1109/CVPR52733.2024.02425</mixed-citation><mixed-citation xml:lang="en">Yu F., Gu J., Li Z., Liu J., Kong X., Wang X., He J., Qiao Y., Dong C. Scaling Up to Excellence: practicing model scaling for photorealistic image restoration in the wild. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 25669–25680. https://doi.org/10.1109/CVPR52733.2024.02425</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang R., Isola P., Efros A.A., Shechtman E., Wang O. The unreasonable effectiveness of deep features as a perceptual metric // Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2018. P. 586–595. https://doi.org/10.1109/CVPR.2018.00068</mixed-citation><mixed-citation xml:lang="en">Zhang R., Isola P., Efros A.A., Shechtman E., Wang O. The unreasonable effectiveness of deep features as a perceptual metric. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 586–595. https://doi.org/10.1109/CVPR.2018.00068</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Wang J., Chan K.C.K., Loy C.C. Exploring CLIP for assessing the look and feel of images // Proc. of the 37th AAAI Conference on Artificial Intelligence. 2023. V. 37. N 2. P. 2555–2563. https://doi.org/10.1609/aaai.v37i2.25353</mixed-citation><mixed-citation xml:lang="en">Wang J., Chan K.C.K., Loy C.C. Exploring CLIP for assessing the look and feel of images. Proc. of the 37th AAAI Conference on Artificial Intelligence, 2023, vol. 37, no. 2. pp. 2555–2563. https://doi.org/10.1609/aaai.v37i2.25353</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Heusel M., Ramsauer H., Unterthiner T., Nessler B., Hochreiter S. GANs trained by a two time-scale update rule converge to a local nash equilibrium // Proc. of the 31st International Conference on Neural Information Processing Systems (NIPS ‘17). 2017. P. 6629–6640.</mixed-citation><mixed-citation xml:lang="en">Heusel M., Ramsauer H., Unterthiner T., Nessler B., Hochreiter S. GANs trained by a two time-scale update rule converge to a local nash equilibrium. Proc. of the 31st International Conference on Neural Information Processing Systems (NIPS ‘17), 2017, pp. 6629–6640.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
