This paper proposes a novel approach for the classification of 3D shapes exploiting surface and volumetric clues inside a deep learning framework. The proposed algorithm uses three different data representations. The first is a set of depth maps obtained by rendering the 3D object. The second is a novel volumetric representation obtained by counting the number of filled voxels along each direction. Finally NURBS surfaces are fitted over the 3D object and surface curvature parameters are selected as the third representation. All the three data representations are fed to a multi-branch Convolutional Neural Network. Each branch processes a different data source and produces a feature vector by using convolutional layers of progressively reduced resolution. The extracted feature vectors are fed to a linear classifier that combines the outputs in order to get the final predictions. Experimental results on the ModelNet dataset show that the proposed approach is able to obtain a state-of-the-art performance.
Deep learning for 3D shape classification based on volumetric density and surface approximation clues
MINTO, LUDOVICO;Pietro Zanuttigh;Giampaolo Pagnutti
2018
Abstract
This paper proposes a novel approach for the classification of 3D shapes exploiting surface and volumetric clues inside a deep learning framework. The proposed algorithm uses three different data representations. The first is a set of depth maps obtained by rendering the 3D object. The second is a novel volumetric representation obtained by counting the number of filled voxels along each direction. Finally NURBS surfaces are fitted over the 3D object and surface curvature parameters are selected as the third representation. All the three data representations are fed to a multi-branch Convolutional Neural Network. Each branch processes a different data source and produces a feature vector by using convolutional layers of progressively reduced resolution. The extracted feature vectors are fed to a linear classifier that combines the outputs in order to get the final predictions. Experimental results on the ModelNet dataset show that the proposed approach is able to obtain a state-of-the-art performance.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.