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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish
Title of host publicationGRAPP
EditorsKadi Bouatouch, A. Augusto Sousa, Jose Braz
PublisherSciTePress
Pages179-190
Number of pages12
ISBN (Electronic)9789897584022
Publication statusPublished - 2020
Event15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2020 - Valletta, Malta
Duration: 2020 Feb 272020 Feb 29

Publication series

NameVISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Volume1

Conference

Conference15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2020
CountryMalta
CityValletta
Period20/2/2720/2/29

Keywords

  • 3D reconstruction
  • Car
  • Deep learning
  • Lazy learning
  • Sketch-based interface

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Single sketch image based 3D car shape reconstruction with deep learning and lazy learning'. Together they form a unique fingerprint.

Cite this