Multistage Model for Robust Face Alignment Using Deep Neural Networks

TL;DR

This paper introduces a multistage deep neural network model for robust face alignment under challenging conditions like occlusions and pose variations, combining spatial transformer networks, hourglass networks, and shape constraints.

Contribution

It presents a novel multistage framework integrating spatial transformer GANs, hourglass networks, and exemplar-based shape constraints for improved face alignment accuracy.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively handles occlusions and pose variations.

Improves landmark localization accuracy.

Abstract

An ability to generalize unconstrained conditions such as severe occlusions and large pose variations remains a challenging goal to achieve in face alignment. In this paper, a multistage model based on deep neural networks is proposed which takes advantage of spatial transformer networks, hourglass networks and exemplar-based shape constraints. First, a spatial transformer - generative adversarial network which consists of convolutional layers and residual units is utilized to solve the initialization issues caused by face detectors, such as rotation and scale variations, to obtain improved face bounding boxes for face alignment. Then, stacked hourglass network is employed to obtain preliminary locations of landmarks as well as their corresponding scores. In addition, an exemplar-based shape dictionary is designed to determine landmarks with low scores based on those with high scores. By incorporating face shape constraints, misaligned landmarks caused by occlusions or cluttered backgrounds can be considerably improved. Extensive experiments based on challenging benchmark datasets are performed to demonstrate the superior performance of the proposed method over other state-of-the-art methods.