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

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトルGRAPP
編集者Kadi Bouatouch, A. Augusto Sousa, Jose Braz
出版社SciTePress
ページ179-190
ページ数12
ISBN(電子版)9789897584022
出版ステータスPublished - 2020
イベント15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2020 - Valletta, Malta
継続期間: 2020 2月 272020 2月 29

出版物シリーズ

名前VISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
1

Conference

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

ASJC Scopus subject areas

  • コンピュータ グラフィックスおよびコンピュータ支援設計
  • コンピュータ サイエンスの応用
  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Single sketch image based 3D car shape reconstruction with deep learning and lazy learning」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル