Deep Face Feature for Face Alignment

TL;DR

This paper introduces a deep learning-based face feature extraction method trained on a large synthetic dataset, significantly improving face alignment accuracy in unconstrained images.

Contribution

It presents a novel deep face feature (DFF) trained on synthesized multi-view face images, enhancing face alignment and matching tasks.

Findings

Achieves state-of-the-art face alignment results.

DFF outperforms general-purpose features for face tasks.

Robustness under highly unconstrained conditions.

Abstract

In this paper, we present a deep learning based image feature extraction method designed specifically for face images. To train the feature extraction model, we construct a large scale photo-realistic face image dataset with ground-truth correspondence between multi-view face images, which are synthesized from real photographs via an inverse rendering procedure. The deep face feature (DFF) is trained using correspondence between face images rendered from different views. Using the trained DFF model, we can extract a feature vector for each pixel of a face image, which distinguishes different facial regions and is shown to be more effective than general-purpose feature descriptors for face-related tasks such as matching and alignment. Based on the DFF, we develop a robust face alignment method, which iteratively updates landmarks, pose and 3D shape. Extensive experiments demonstrate that our method can achieve state-of-the-art results for face alignment under highly unconstrained face images.