The Visual Computer

, Volume 32, Issue 6–8, pp 717–727

3D cartoon face generation by local deformation mapping

Original Article

DOI: 10.1007/s00371-016-1265-5

Cite this article as:
Zhou, J., Tong, X., Liu, Z. et al. Vis Comput (2016) 32: 717. doi:10.1007/s00371-016-1265-5
  • 278 Downloads

Abstract

We present a data-driven method for automatically generating a 3D cartoon of a real 3D face. Given a sparse set of 3D real faces and their corresponding cartoon faces modeled by an artist, our method models the face in each subspace as the deformation of its nearby exemplars and learn a mapping between the deformations defined by the real faces and their cartoon counterparts. To reduce the exemplars needed for learning, we regress a collection of linear mappings defined locally in both face geometry and identity spaces and develop a progressive scheme for users to gradually add new exemplars for training. At runtime, our method first finds the nearby exemplars of an input real face and then constructs the result cartoon face from the corresponding cartoon faces of the nearby real face exemplars and the local deformations mapped from the real face subspace. Our method greatly simplifies the cartoon generation process by learning artistic styles from a sparse set of exemplars. We validate the efficiency and effectiveness of our method by applying it to faces of different facial features. Results demonstrate that our method not only preserves the artistic style of the exemplars, but also keeps the unique facial geometric features of different identities.

Keywords

3D cartoon generation Local deformation mapping Data-driven method 

Supplementary material

371_2016_1265_MOESM1_ESM.pdf (5 mb)
Supplementary material 1 (pdf 5145 KB)

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  • Jingyong Zhou
    • 1
  • Xin Tong
    • 2
  • Zicheng Liu
    • 3
  • Baining Guo
    • 1
    • 2
  1. 1.Tsinghua UniversityBeijingChina
  2. 2.Microsoft ResearchBeijingChina
  3. 3.Microsoft ResearchRedmondUSA

Personalised recommendations