Abstract: Provided are methods, systems, and computer-readable medium for synthetically generating training data to be used to train a learning algorithm that is capable of generating computer-generated images of a subject from real images that include the subject. The training data can be generated using a facial rig by changing expressions, camera viewpoints, and illumination in the training data. The training data can then be used for tracking faces in a real-time video stream. In such examples, the training data can be tuned to expected environmental conditions and camera properties of the real-time video stream. Provided herein are also strategies to improve training set construction by analyzing which attributes of a computer-generated image (e.g., expression, viewpoint, and illumination) require denser sampling.

Abstract: Embodiments can provide adaptive image filtering. Under this approach, image quality can be enhanced by adjusting an approximation function to better adapt image signals in different parts of an image. Certain parts of the image may be enhanced using a certain approximation function while some other parts of the image may be enhanced using a different approximation function. In certain embodiments, the approximation function selected for a part of the image can be a polynomial function having a specific order. The specific polynomial order can be applied directly to obtain an estimated image value of the part of the image. In certain embodiments, the estimation of the reconstruction error can include iteratively estimating a bias term of the reconstruction error and a variance term of the reconstruction error.

Abstract: Embodiments can provide adaptive image filtering. Under this approach, image quality can be enhanced by adjusting an approximation function to better adapt image signals in different parts of an image. Certain parts of the image may be enhanced using a certain approximation function while some other parts of the image may be enhanced using a different approximation function. In certain embodiments, the approximation function selected for a part of the image can be a polynomial function having a specific order. The specific polynomial order can be applied directly to obtain an estimated image value of the part of the image. In certain embodiments, the estimation of the reconstruction error can include iteratively estimating a bias term of the reconstruction error and a variance term of the reconstruction error.