SCITEPRESS - SCIENCE AND TECHNOLOGY PUBLICATIONS

<!DOCTYPE html> <html> <head> <meta charset="utf-8"> <title>SCITEPRESS - SCIENCE AND TECHNOLOGY PUBLICATIONS</title> <meta name ="description" content="Digital Library" /> <meta name="citation_language" content="en"> <meta name="citation_title" content="Can We Use Neural Regularization to Solve Depth Super-resolution?"> <meta name="citation_abstract" content="Depth maps captured with commodity sensors often require super-resolution to be used in applications. In this work we study a super-resolution approach based on a variational problem statement with Tikhonov regularization where the regularizer is parametrized with a deep neural network. This approach was previously applied successfully in photoacoustic tomography. We experimentally show that its application to depth map super-resolution is difficult, and provide suggestions about the reasons for that."> <meta name="citation_publication_date" content="2022/02/06"> <meta name="citation_conference_title" content="International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP)"> <meta name="citation_keywords" content="Depth Super-Resolution; Neural Regularization; 3D Deep Learning;"> <meta name="citation_doi" content="10.5220/0010883500003124"> <meta name="citation_isbn" content="978-989-758-555-5"> <meta name="citation_volume" content="2"> <meta name="citation_firstpage" content="582"> <meta name="citation_lastpage" content="590"> <meta name="citation_publisher" content="SCITEPRESS"> <meta name="citation_author" content="Milena Gazdieva" > <meta name="citation_author_institution" content="Skolkovo Institute of Science and Technology, Moscow, Russia" > <meta name="citation_author" content="Oleg Voynov" > <meta name="citation_author_institution" content="Skolkovo Institute of Science and Technology, Moscow, Russia" > <meta name="citation_author" content="Alexey Artemov" > <meta name="citation_author_institution" content="Skolkovo Institute of Science and Technology, Moscow, Russia" > <meta name="citation_author" content="Youyi Zheng" > <meta name="citation_author_institution" content="State Key Lab, Zhejiang University, Hangzhou, China" > <meta name="citation_author" content="Luiz Velho" > <meta name="citation_author_institution" content="Instituto Nacional de Matem谩tica Pura e Aplicada, Rio de Janeiro, Brazil" > <meta name="citation_author" content="Evgeny Burnaev" > <meta name="citation_author_institution" content="Skolkovo Institute of Science and Technology, Moscow, Russia" > <meta name="citation_abstract_html_url" content="/PublishedPapers/2022/108835"> <meta name="citation_pdf_url" content="/PublishedPapers/2022/108835/108835.pdf"> </head> <body> <article> <a href="/publishedPapers/2022/108835/pdf/index.html"><h1 class="citation_title">Can We Use Neural Regularization to Solve Depth Super-resolution?</h1></a> <h3 class="citation_author"> Milena Gazdieva, Oleg Voynov, Alexey Artemov, Youyi Zheng, Luiz Velho, Evgeny Burnaev</h3> <h4 class="citation_publication_date">2022</h4> <h4>Abstract</h4> <p class="citation_abstract">Depth maps captured with commodity sensors often require super-resolution to be used in applications. In this work we study a super-resolution approach based on a variational problem statement with Tikhonov regularization where the regularizer is parametrized with a deep neural network. This approach was previously applied successfully in photoacoustic tomography. We experimentally show that its application to depth map super-resolution is difficult, and provide suggestions about the reasons for that.</p> <a href="/PublishedPapers/2022/108835/108835.pdf" class="citation_pdf_url">Download</a> <br /> <br /> <br/> <h4 style="margin:0;">Paper Citation</h4> <br/> <h4 style="margin:0;">in Harvard Style</h4> <p style="margin:0;">Gazdieva M., Voynov O., Artemov A., Zheng Y., Velho L. and Burnaev E. (2022). <b>Can We Use Neural Regularization to Solve Depth Super-resolution?</b>. In <i>Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP</i>; ISBN 978-989-758-555-5, SciTePress, pages 582-590. DOI: 10.5220/0010883500003124</p> <br/> <h4 style="margin:0;">in Bibtex Style</h4> <p style="margin:0;">@conference{visapp22,<br />author={Milena Gazdieva and Oleg Voynov and Alexey Artemov and Youyi Zheng and Luiz Velho and Evgeny Burnaev},<br />title={Can We Use Neural Regularization to Solve Depth Super-resolution?},<br />booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP},<br />year={2022},<br />pages={582-590},<br />publisher={SciTePress},<br />organization={INSTICC},<br />doi={10.5220/0010883500003124},<br />isbn={978-989-758-555-5},<br />}</p> <br/> <h4 style="margin:0;">in EndNote Style</h4> <p style="margin:0;">TY - CONF <br /><br />JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 4: VISAPP<br />TI - Can We Use Neural Regularization to Solve Depth Super-resolution?<br />SN - 978-989-758-555-5<br />AU - Gazdieva M. <br />AU - Voynov O. <br />AU - Artemov A. <br />AU - Zheng Y. <br />AU - Velho L. <br />AU - Burnaev E. <br />PY - 2022<br />SP - 582<br />EP - 590<br />DO - 10.5220/0010883500003124<br />PB - SciTePress<br /></p> <br/> </article> </body> </html>

CINXE.COM

SCITEPRESS - SCIENCE AND TECHNOLOGY PUBLICATIONS