Single Sketch Image based 3D Car Shape Reconstruction with Deep Learning and Lazy Learning

Naoki Nozawa, Hubert P. H. Shum, Edmond S. L. Ho, Shigeo Morishima

2020

Abstract

Efficient car shape design is a challenging problem in both the automotive industry and the computer animation/games industry. In this paper, we present a system to reconstruct the 3D car shape from a single 2D sketch image. To learn the correlation between 2D sketches and 3D cars, we propose a Variational Autoencoder deep neural network that takes a 2D sketch and generates a set of multi-view depth and mask images, which form a more effective representation comparing to 3D meshes, and can be effectively fused to generate a 3D car shape. Since global models like deep learning have limited capacity to reconstruct fine-detail features, we propose a local lazy learning approach that constructs a small subspace based on a few relevant car samples in the database. Due to the small size of such a subspace, fine details can be represented effectively with a small number of parameters. With a low-cost optimization process, a high-quality car shape with detailed features is created. Experimental results show that the system performs consistently to create highly realistic cars of substantially different shape and topology.

Download


Paper Citation


in Harvard Style

Nozawa N., Shum H., Ho E. and Morishima S. (2020). Single Sketch Image based 3D Car Shape Reconstruction with Deep Learning and Lazy Learning. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 1: GRAPP; ISBN 978-989-758-402-2, SciTePress, pages 179-190. DOI: 10.5220/0009157001790190


in Bibtex Style

@conference{grapp20,
author={Naoki Nozawa and Hubert P. H. Shum and Edmond S. L. Ho and Shigeo Morishima},
title={Single Sketch Image based 3D Car Shape Reconstruction with Deep Learning and Lazy Learning},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 1: GRAPP},
year={2020},
pages={179-190},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009157001790190},
isbn={978-989-758-402-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 1: GRAPP
TI - Single Sketch Image based 3D Car Shape Reconstruction with Deep Learning and Lazy Learning
SN - 978-989-758-402-2
AU - Nozawa N.
AU - Shum H.
AU - Ho E.
AU - Morishima S.
PY - 2020
SP - 179
EP - 190
DO - 10.5220/0009157001790190
PB - SciTePress