000150269 001__ 150269 000150269 005__ 20250201165030.0 000150269 0247_ $$2doi$$a10.1109/CVPR.2019.01210 000150269 0248_ $$2sideral$$a122982 000150269 037__ $$aART-2019-122982 000150269 041__ $$aeng 000150269 100__ $$aFacil, J.M.$$uUniversidad de Zaragoza 000150269 245__ $$aCam-CONVS: Camera-aware multi-scale convolutions for single-view depth 000150269 260__ $$c2019 000150269 5060_ $$aAccess copy available to the general public$$fUnrestricted 000150269 5203_ $$aSingle-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model. Thus, changing the camera model requires collecting an entirely new training dataset. In this work, we propose a new type of convolution that can take the camera parameters into account, thus allowing neural networks to learn calibration-aware patterns. Experiments confirm that this improves the generalization capabilities of depth prediction networks considerably, and clearly outperforms the state of the art when the train and test images are acquired with different cameras. 000150269 536__ $$9info:eu-repo/grantAgreement/ES/DGA-FSE/T45-17R$$9info:eu-repo/grantAgreement/EC/H2020/688007/EU/A gardening robot for rose, hedge and topiary trimming/TrimBot2020$$9This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 688007-TrimBot2020$$9info:eu-repo/grantAgreement/ES/MINECO/DPI2015-67275 000150269 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/ 000150269 592__ $$a13.396$$b2019 000150269 593__ $$aSoftware$$c2019 000150269 593__ $$aComputer Vision and Pattern Recognition$$c2019 000150269 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion 000150269 700__ $$aUmmenhofer, B. 000150269 700__ $$aZhou, H. 000150269 700__ $$0(orcid)0000-0003-1183-349X$$aMontesano, L.$$uUniversidad de Zaragoza 000150269 700__ $$aBrox, T. 000150269 700__ $$0(orcid)0000-0003-1368-1151$$aCivera, J.$$uUniversidad de Zaragoza 000150269 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát. 000150269 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf. 000150269 773__ $$g2019 (2019), 11818-11827$$pProc.- IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.$$tProceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition$$x1063-6919 000150269 8564_ $$s6343891$$uhttps://zaguan.unizar.es/record/150269/files/texto_completo.pdf$$yPostprint 000150269 8564_ $$s2608525$$uhttps://zaguan.unizar.es/record/150269/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint 000150269 909CO $$ooai:zaguan.unizar.es:150269$$particulos$$pdriver 000150269 951__ $$a2025-02-01-14:36:42 000150269 980__ $$aARTICLE