Convolutional Experts Constrained Local Model for Facial Landmark Detection
This addresses the need for more accurate and robust facial landmark detection in computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of facial landmark detection by introducing a Convolutional Experts Constrained Local Model (CE-CLM) algorithm, which outperforms state-of-the-art baselines by a large margin on four public datasets, especially on challenging profile images.
Constrained Local Models (CLMs) are a well-established family of methods for facial landmark detection. However, they have recently fallen out of favor to cascaded regression-based approaches. This is in part due to the inability of existing CLM local detectors to model the very complex individual landmark appearance that is affected by expression, illumination, facial hair, makeup, and accessories. In our work, we present a novel local detector -- Convolutional Experts Network (CEN) -- that brings together the advantages of neural architectures and mixtures of experts in an end-to-end framework. We further propose a Convolutional Experts Constrained Local Model (CE-CLM) algorithm that uses CEN as local detectors. We demonstrate that our proposed CE-CLM algorithm outperforms competitive state-of-the-art baselines for facial landmark detection by a large margin on four publicly-available datasets. Our approach is especially accurate and robust on challenging profile images.