131266 20240207154753.0 doi 10.1109/ICRA48891.2023.10161142 sideral 136755 ART-2023-136755 spa Berenguel-Baeta, Bruno Universidad de Zaragoza (orcid)0000-0003-2674-4844 Fredsnet: joint monocular depth and semantic segmentation with fast fourier convolutions from single panoramas 2023 In this work we present FreDSNet, a deep learning solution which obtains semantic 3D understanding of indoor environments from single panoramas. Omnidirectional images reveal task-specific advantages when addressing scene understanding problems due to the 360-degree contextual information about the entire environment they provide. However, the inherent characteristics of the omnidirectional images add additional problems to obtain an accurate detection and segmentation of objects or a good depth estimation. To overcome these problems, we exploit convolutions in the frequential domain obtaining a wider receptive field in each convolutional layer. These convolutions allow to leverage the whole context information from omnidirectional images. FreDSNet is the first network that jointly provides monocular depth estimation and semantic segmentation from a single panoramic image exploiting fast Fourier convolutions. Our experiments show that FreDSNet has slight better performance than the sole state-of-the-art method that obtains both semantic segmentation and depth estimation from panoramas. FreDSNet code is publicly available in https://github.com/Sbrunoberenguel/FreDSNet Access copy available to the general public Unrestricted info:eu-repo/grantAgreement/ES/MICINN-AEI/PID2021-125209OB-I00 info:eu-repo/grantAgreement/EUR/MICINN/TED2021-129410B-I00 info:eu-repo/grantAgreement/ES/UZ/JIUZ-2021-TEC-01 info:eu-repo/semantics/openAccess All rights reserved http://www.europeana.eu/rights/rr-f/ info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/acceptedVersion Bermúdez-Cameo, Jesús Universidad de Zaragoza (orcid)0000-0002-8479-1748 Guerrero, José J. Universidad de Zaragoza (orcid)0000-0001-5209-2267 5007 520 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Ingen.Sistemas y Automát. (2023), 2152-4092 IEEE Int. conf. robot. autom. IEEE International Conference on Robotics and Automation 2152-4092 5183536 http://zaguan.unizar.es/record/131266/files/texto_completo.pdf Postprint 3167885 http://zaguan.unizar.es/record/131266/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:131266 articulos driver 2024-02-07-14:35:52 ARTICLE