Face Manifold: Manifold Learning for Synthetic Face Generation

TL;DR

This paper introduces a face manifold learning approach that generates diverse, realistic synthetic face datasets by addressing non-possible faces and preserving diversity, improving over existing methods.

Contribution

The paper presents a novel face manifold learning method that effectively denoises corrupted faces and enhances synthetic face dataset diversity, outperforming prior techniques.

Findings

The method successfully denoises highly corrupted faces.

Generated datasets show higher diversity both qualitatively and quantitatively.

Outperforms state-of-the-art methods significantly.

Abstract

Face is one of the most important things for communication with the world around us. It also forms our identity and expressions. Estimating the face structure is a fundamental task in computer vision with applications in different areas such as face recognition and medical surgeries. Recently, deep learning techniques achieved significant results for 3D face reconstruction from flat images. The main challenge of such techniques is a vital need for large 3D face datasets. Usually, this challenge is handled by synthetic face generation. However, synthetic datasets suffer from the existence of non-possible faces. Here, we propose a face manifold learning method for synthetic diverse face dataset generation. First, the face structure is divided into the shape and expression groups. Then, a fully convolutional autoencoder network is exploited to deal with the non-possible faces, and, simultaneously, preserving the dataset diversity. Simulation results show that the proposed method is capable of denoising highly corrupted faces. The diversity of the generated dataset is evaluated qualitatively and quantitatively and compared to the existing methods. Experiments show that our manifold learning method outperforms the state of the art methods significantly.