Face reconstruction from partial information based on a morphable face model

This paper proposes a method for reconstructing a whole face image from partial information based on a morphable face model. Faces are modeled by linear combinations of prototypes of shape and texture. With the shape and texture information of pixels in an given region, we can estimate optimal coefficients for linear combinations of prototypes of shape and texture. In such an over-determined condition, where the number of pixels in the given region is greater than the number of prototypes, we find an optimal solution using projection for least square minimization (LSM). Our experimental results show that reconstructed faces are very natural and plausible like real photos. We interpret the encouraging performance of our proposed method as evidence in support of the hypothesis that the human visual system may reconstruct an whole information from partial information using prototypical examples.