Abstract: A system, method, and apparatus for generating a normalization of a single two-dimensional image of an unconstrained human face. The system receives the single two-dimensional image of the unconstrained human face, generates an undistorted face based on the unconstrained human face by removing perspective distortion from the unconstrained human face via a perspective undistortion network, generates an evenly lit face based on the undistorted face by normalizing lighting of the undistorted face via a lighting translation network, and generates a frontalized and neutralized expression face based on the evenly lit face via an expression neutralization network.

Abstract: A system and method for generating real-time facial animation is disclosed. The system relies upon pre-generating a series of key expression images from a single neutral image using a pre-trained generative adversarial neural network. The key expression images are used to generate a set of FACS expressions and associated textures which may be applied to a three-dimensional model to generate facial animation. The FACS expressions and textures may be provided to a mobile device to enable that mobile device to generate convincing three-dimensional avatars in real-time with convincing animation in a processor non-intensive way through a blending process using the pre-determined FACS expressions and textures.

Abstract: A system for generating three-dimensional facial models including photorealistic hair and facial textures includes creating a facial model with reliance upon neural networks based upon a single two-dimensional input image. The photorealistic hair is created by finding a subset of similar three-dimensional polystrip hairstyles from a large database of polystrip hairstyles, selecting the most-alike polystrip hairstyle, deforming that polystrip hairstyle to better fit the hair of the two-dimensional image. Then, collisions and bald spots are corrected, and suitable textures are applied. Finally, the facial model and polystrip hairstyle are combined into a final three-dimensional avatar.

Abstract: A method for generating three-dimensional facial models and photorealistic textures from inferences using deep neural networks relies upon generating a low frequency and a high frequency albedo map of the full and partial face, respectively. Then, the high frequency albedo map may be used for comparison with correlation matrices generated by a neural network trained by a large scale, high-resolution facial dataset with simulated partial visibility. The corresponding correlation matrices of the complete facial textures can then be retrieved. Finally, a full facial texture map may be synthesized, using convex combinations of the correlation matrices. A photorealistic facial texture for the three-dimensional face rendering can be obtained through optimization using the deep neural network and a loss function that incorporates the blended target correlation matrices.

Abstract: There is disclosed a system and method for training a set of expression and neutral convolutional neural networks using a single performance mapped to a set of known phonemes and visemes in the form predetermined sentences and facial expressions. Then, subsequent training of the convolutional neural networks can occur using temporal data derived from audio data within the original performance mapped to a set of professionally-created three dimensional animations. Thereafter, with sufficient training, the expression and neutral convolutional neural networks can generate facial animations from facial image data in real-time without individual specific training.

Abstract: There is disclosed a system and method of performing facial recognition from RGB image data. The method includes generating a lower-resolution image from the RGB image data, performing a convolution of the lower-resolution image data to derive a probability map identifying probable facial regions and a probable non-facial regions, and performing a first deconvolution on the lower-resolution image using a bilinear interpolation layer to derive a set of coarse facial segments. The method further includes performing a second deconvolution on the lower-resolution image using a series of unpooling, deconvolution, and rectification layers to derive a set of fine facial segments, concatenating the set of coarse facial segments to the set of fine facial segments to create an image matrix made up of a set of facial segments, and generating a binary facial mask identifying probable facial regions and probable non-facial regions from the image matrix.