1 code implementation • 30 Jun 2023 • Hamza Bouzid, Lahoucine Ballihi
A lightweight auto-encoder, based on spiral convolutions, is employed to extract spatial geometrical features from each 3D mesh.
no code implementations • Intelligent Systems with Applications 2022 • Hamza Bouzid, Lahoucine Ballihi
Starting from a single neutral facial image and a label indicating the desired facial expression, we aim to synthesize a video of the given identity performing the specified facial expression.