Recovering 3D facial shape via coupled 2D/3D space learning

Abstract

This paper presents a method for recovering 3D facial shape from single image via learning the relationship between the 2D intensity images and the 3D facial shapes. With a coupled training set, the intensity images and their corresponding facial shapes make up two vector spaces respectively. But only the correlated components in both spaces are useful for inference, so there must be embedded hidden subspaces in each space which preserve the interspace correlation information. Thus by learning the projection onto hidden subspaces based on Maximum Correlation Criteria and optimizing the linear transform between the hidden spaces, 3D facial shape is inferred from the intensity image. The effectiveness of the method is demonstrated on both synthesized and real world data.

3D Face Model Estimation based on Similarity Transform using Differential Evolution Optimization

“…Learning based algorithms exploit the common information shared by the 2D image subspaces and 3-D shape to recover the 3-D shape 13 . Thus the algorithms in this category require a coupled training set comprising of 2D and corresponding 3D faces.…”