150269 20251017144607.0 doi 10.1109/CVPR.2019.01210 sideral 122982 ART-2019-122982 eng Facil, J.M. Universidad de Zaragoza Cam-CONVS: Camera-aware multi-scale convolutions for single-view depth 2019 Access copy available to the general public Unrestricted Single-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. info:eu-repo/grantAgreement/ES/DGA-FSE/T45-17R info:eu-repo/grantAgreement/EC/H2020/688007/EU/A gardening robot for rose, hedge and topiary trimming/TrimBot2020 This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 688007-TrimBot2020 info:eu-repo/grantAgreement/ES/MINECO/DPI2015-67275 info:eu-repo/semantics/openAccess All rights reserved http://www.europeana.eu/rights/rr-f/ 13.396 2019 Software 2019 Computer Vision and Pattern Recognition 2019 info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Ummenhofer, B. Zhou, H. Montesano, L. Universidad de Zaragoza (orcid)0000-0003-1183-349X Brox, T. Civera, J. Universidad de Zaragoza (orcid)0000-0003-1368-1151 5007 520 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Ingen.Sistemas y Automát. 5007 570 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Lenguajes y Sistemas Inf. 2019 (2019), 11818-11827 Proc.- IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1063-6919 6343891 http://zaguan.unizar.es/record/150269/files/texto_completo.pdf Postprint 2608525 http://zaguan.unizar.es/record/150269/files/texto_completo.jpg?subformat=icon icon Postprint oai:zaguan.unizar.es:150269 articulos driver 2025-10-17-14:15:53 ARTICLE