Premium
Image‐based Shaving
Author(s) -
Nguyen Minh Hoai,
Lalonde JeanFrancois,
Efros Alexei A.,
De la Torre Fernando
Publication year - 2008
Publication title -
computer graphics forum
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.578
H-Index - 120
eISSN - 1467-8659
pISSN - 0167-7055
DOI - 10.1111/j.1467-8659.2008.01160.x
Subject(s) - computer science , linear subspace , face (sociological concept) , layer (electronics) , subspace topology , image synthesis , artificial intelligence , computer vision , computer graphics (images) , image (mathematics) , pattern recognition (psychology) , mathematics , social science , chemistry , geometry , organic chemistry , sociology
Many categories of objects, such as human faces, can be naturally viewed as a composition of several different layers. For example, a bearded face with glasses can be decomposed into three layers: a layer for glasses, a layer for the beard and a layer for other permanent facial features. While modeling such a face with a linear subspace model could be very difficult, layer separation allows for easy modeling and modification of some certain structures while leaving others unchanged. In this paper, we present a method for automatic layer extraction and its applications to face synthesis and editing. Layers are automatically extracted by utilizing the differences between subspaces and modeled separately. We show that our method can be used for tasks such beard removal (virtual shaving), beard synthesis, and beard transfer, among others.