Super-Resolution of Faces Using Texture Mapping on a Generic 3D Model

Abstract

This paper proposes a novel face texture mapping framework to transform faces with different poses into a unique texture map. Under this framework, texture mapping can be realized by utilizing a generic 3D face model, standard Haar-like feature based detector, active appearance model and pose estimation algorithm. By this texture map, correspondence of every pixel at the face across multiple distinct input images can then be established, which enables super-resolution algorithms to be applied directly on registered texture map to render high resolution faces. This paper details the proposed framework, and illustrates how the proposed super-resolution algorithm works with the help of weighted average and median filters. Convincing experimental results are also presented to validate the effectiveness of the proposed framework and superresolution algorithm.

Dense point-to-point correspondences between 3D faces using parametric remeshing for constructing 3D Morphable Models

“…The accuracy of the correspondences determines the quality of the 3D face model and the performance of the whole application. Besides building a 3DMM also other tasks can be performed with exact point-to-point correspondences between 3D faces, such as morphing [5], expression cloning [12,13,19,20], and texture mapping [7,23].…”