Face Alignment by Local Deep Descriptor Regression

TL;DR

This paper introduces Local Deep Descriptor Regression (LDDR), a novel face alignment method using CNN-derived local descriptors that accurately localize facial landmarks across various conditions, outperforming existing algorithms.

Contribution

The paper proposes a new local deep descriptor computation method and integrates it into a face alignment algorithm that handles pose, size, and occlusion variations effectively.

Findings

LDDR achieves higher accuracy than state-of-the-art face alignment methods.

Deep descriptors can replace traditional features like SIFT and HOG.

Extensive tests on five datasets validate the method's robustness.

Abstract

We present an algorithm for extracting key-point descriptors using deep convolutional neural networks (CNN). Unlike many existing deep CNNs, our model computes local features around a given point in an image. We also present a face alignment algorithm based on regression using these local descriptors. The proposed method called Local Deep Descriptor Regression (LDDR) is able to localize face landmarks of varying sizes, poses and occlusions with high accuracy. Deep Descriptors presented in this paper are able to uniquely and efficiently describe every pixel in the image and therefore can potentially replace traditional descriptors such as SIFT and HOG. Extensive evaluations on five publicly available unconstrained face alignment datasets show that our deep descriptor network is able to capture strong local features around a given landmark and performs significantly better than many competitive and state-of-the-art face alignment algorithms.