SR-VFA: Accurate Self-Refined Face Alignment in Videos

Face alignment is a critical and difficult task for many facial analysis applications. Existing VFA methods frequently ignore the consistency of facial geometries and textures across video sequences, limiting their ability to handle accurate and stable face alignment. This paper describes a robust and highly accurate 3D Morphable Model (3DMM)-based VFA approach that employs a novel texture generation method and a self-refined face alignment procedure. Our method iteratively fine-tunes facial geometries, textures, and poses by using a differentiable rendering technique and a self-refined optimization method. Experiment results show that our method outperforms existing state-of-the-art methods in terms of both accuracy and temporal stability. Visual results and source code are available at: https://pawindergit.github.io/SR-VFA/