Sfikas, KonstantinosTheoharis, TheoharisPratikakis, IoannisIoannis Pratikakis and Florent Dupont and Maks Ovsjanikov2017-04-222017-04-222017978-3-03868-030-71997-0471https://doi.org/10.2312/3dor.20171045https://diglib.eg.org:443/handle/10.2312/3dor20171045A novel 3D model classification and retrieval method, based on the PANORAMA representation and Convolutional Neural Networks, is presented. Initially, the 3D models are pose normalized using the SYMPAN method and consecutively the PANORAMA representation is extracted and used to train a convolutional neural network. The training is based on an augmented view of the extracted panoramic representation views. The proposed method is tested in terms of classification and retrieval accuracy on standard large scale datasets.I.3.6 [Computer Graphics]Methodology and TechniquesI.3.7 [Computer Graphics]Three Dimensional Graphics and RealismVisible line/surface algorithmsI.3.3 [Computer Graphics]Picture/Image GenerationViewing AlgorithmsI.5.1 [Pattern Recognition]ModelsNeural Nets10.2312/3dor.201710451-7