Abstract | ||
---|---|---|
Proposes a method for reconstructing partially occluded faces based on a 2D morphable model. Faces are modeled by linear combinations of prototypes of shape and texture. With the shape and texture information only from an unoccluded 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 points in the unoccluded region is greater than the number of prototypes, we find an optimal solution using a simple least square minimization method. Our experimental results show that reconstructed faces are very natural and plausible like real photos. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1109/ICPR.2002.1048315 | ICPR (2) |
Keywords | Field | DocType |
2d morphable model,face reconstruction,morphable face model,partially occluded faces,rendering (computer graphics),image reconstruction,least squares approximations,optimal coefficients,shape,minimisation,image texture,least square minimization method,texture,prototypes,computer science,computed tomography,least square,degradation | Least squares,Iterative reconstruction,Linear combination,Computer vision,Pattern recognition,Image texture,Computer science,Minification,Minimisation (psychology),Artificial intelligence,Computed tomography | Conference |
Volume | ISSN | Citations |
2 | 1051-4651 | 1 |
PageRank | References | Authors |
0.38 | 1 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bon-Woo Hwang | 1 | 177 | 16.33 |
Seong-Whan Lee | 2 | 3756 | 343.90 |