000162747 001__ 162747
000162747 005__ 20251017144621.0
000162747 0247_ $$2doi$$a10.1049/ipr2.70197
000162747 0248_ $$2sideral$$a145299
000162747 037__ $$aART-2025-145299
000162747 041__ $$aeng
000162747 100__ $$0(orcid)0000-0003-2674-4844$$aBerenguel-Baeta, Bruno$$uUniversidad de Zaragoza
000162747 245__ $$aPanoramic Depth and Semantic Estimation With Frequency and Distortion Aware Convolutions
000162747 260__ $$c2025
000162747 5060_ $$aAccess copy available to the general public$$fUnrestricted
000162747 5203_ $$aOmnidirectional images reveal advantages when addressing the understanding of the environment due to the 360‐degree contextual information. 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 frequency domain, obtaining a wider receptive field in each convolutional layer, and convolutions in the equirectangular projection, to cope with the image distortion. Both convolutions allow to leverage the whole context information from omnidirectional images. Our experiments show that our proposal has better performance on non‐gravity‐oriented panoramas than state‐of‐the‐art methods and similar performance on oriented panoramas as specific state‐of‐the‐art methods for semantic segmentation and for monocular depth estimation, outperforming the sole other method which provides both tasks.
000162747 536__ $$9info:eu-repo/grantAgreement/ES/MICINN-AEI/PID2021-125209OB-I00$$9info:eu-repo/grantAgreement/EUR/MICINN/TED2021-129410B-I00
000162747 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttps://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
000162747 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000162747 700__ $$0(orcid)0000-0002-8479-1748$$aBermudez-Cameo, Jesus$$uUniversidad de Zaragoza
000162747 700__ $$0(orcid)0000-0001-5209-2267$$aGuerrero, Jose J.$$uUniversidad de Zaragoza
000162747 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát.
000162747 773__ $$g19, 1 (2025), e70197 [12 pp.]$$pIET Image Processing$$tIET Image Processing$$x1751-9659
000162747 8564_ $$s8588417$$uhttps://zaguan.unizar.es/record/162747/files/texto_completo.pdf$$yVersión publicada
000162747 8564_ $$s2255587$$uhttps://zaguan.unizar.es/record/162747/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000162747 909CO $$ooai:zaguan.unizar.es:162747$$particulos$$pdriver
000162747 951__ $$a2025-10-17-14:22:01
000162747 980__ $$aARTICLE