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

Nozawa, Naoiki, Shum, Hubert, Ho, Edmond and Morishima, Shigeo (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. SciTePress, pp. 179-190. ISBN 9789897584022

Preview	Text GRAPP_2020_46.pdf - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives 4.0. Download (90MB) | Preview
Preview	Text GRAPP 2020 Compressed.pdf - Accepted Version Download (1MB) | Preview

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 sketchimage. To learn the correlation between 2D sketches and 3D cars, we propose a Variational Autoencoder deepneural network that takes a 2D sketch and generates a set of multi-view depth and mask images, which forma more effective representation comparing to 3D meshes, and can be effectively fused to generate a 3D carshape. Since global models like deep learning have limited capacity to reconstruct fine-detail features, wepropose a local lazy learning approach that constructs a small subspace based on a few relevant car samples inthe database. Due to the small size of such a subspace, fine details can be represented effectively with a smallnumber of parameters. With a low-cost optimization process, a high-quality car shape with detailed featuresis created. Experimental results show that the system performs consistently to create highly realistic cars ofsubstantially different shape and topology.

Actions (login required)

View Item

Downloads