Deep Learning for 3D Shape Classification based on Volumetric Density and Surface Approximation Clues

Ludovico Minto, 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.

Paper Citation

in Harvard Style

Minto L., Zanuttigh P. and Pagnutti G. (2018). Deep Learning for 3D Shape Classification based on Volumetric Density and Surface Approximation Clues. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 317-324. DOI: 10.5220/0006619103170324

in Bibtex Style

@conference{visapp18,
author={Ludovico Minto and Pietro Zanuttigh and Giampaolo Pagnutti},
title={Deep Learning for 3D Shape Classification based on Volumetric Density and Surface Approximation Clues},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={317-324},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006619103170324},
isbn={978-989-758-290-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - Deep Learning for 3D Shape Classification based on Volumetric Density and Surface Approximation Clues
SN - 978-989-758-290-5
AU - Minto L.
AU - Zanuttigh P.
AU - Pagnutti G.
PY - 2018
SP - 317
EP - 324
DO - 10.5220/0006619103170324
PB - SciTePress