Robust Face Alignment Using a Mixture of Invariant Experts

TL;DR

This paper introduces a robust face alignment method that uses a cascade of mixture of experts, each specialized for different poses and expressions, improving accuracy under large variations.

Contribution

The paper presents a novel cascade of regression experts with transformation invariance and deformation constraints for improved face alignment accuracy.

Findings

Outperforms previous methods on public datasets

Handles large pose and expression variations effectively

Increases robustness with deformation constraints

Abstract

Face alignment, which is the task of finding the locations of a set of facial landmark points in an image of a face, is useful in widespread application areas. Face alignment is particularly challenging when there are large variations in pose (in-plane and out-of-plane rotations) and facial expression. To address this issue, we propose a cascade in which each stage consists of a mixture of regression experts. Each expert learns a customized regression model that is specialized to a different subset of the joint space of pose and expressions. The system is invariant to a predefined class of transformations (e.g., affine), because the input is transformed to match each expert's prototype shape before the regression is applied. We also present a method to include deformation constraints within the discriminative alignment framework, which makes our algorithm more robust. Our algorithm significantly outperforms previous methods on publicly available face alignment datasets.