A Sparse and Low-rank approach to efficient face alignment for photo-real talking head synthesis

In this paper, we propose a framework for practical large-scale face alignment, based on the recent development of Robust Alignment by Sparse and Low-rank Decomposition for linearly correlated images (RASL). Unfortunately, the original implementation is not applicable in large image dataset. We extend this technique to deal with the situation with millions of images, with the aid of l₁-regularized least squares. Our proposal is applied onto the photo-real talking head, a challenging application which requires highly precise alignments of faces from video sequences. We verify the efficacy of our algorithm with experiments using real talking head data. Our method attains comparable quality to RASL in the experiments.