ML p(r)ior | Face Alignment by Local Deep Descriptor Regression

Face Alignment by Local Deep Descriptor Regression

2016-01-29
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.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2017-03-13

We propose a novel deep learning architecture for regressing disparity from a rectified pair of ster… show more
PDF

Highlights - Most important sentences from the article

2018-03-21

We propose a straightforward method that simultaneously reconstructs the 3D facial structure and pro… show more
PDF

Highlights - Most important sentences from the article

2016-11-03

We present a multi-purpose algorithm for simultaneous face detection, face alignment, pose estimatio… show more
PDF

Highlights - Most important sentences from the article

2017-06-06

In this paper, we propose Deep Alignment Network (DAN), a robust face alignment method based on a de… show more
PDF

Highlights - Most important sentences from the article

2019-02-09

We present a method for highly efficient landmark detection that combines deep convolutional neural … show more
PDF

Highlights - Most important sentences from the article

2016-05-03
1605.01014 | cs.CV

We propose a novel cascaded framework, namely deep deformation network (DDN), for localizing landmar… show more
PDF

Highlights - Most important sentences from the article

2018-08-05

Facial landmarks are highly correlated with each other since a certain landmark can be estimated by … show more
PDF

Highlights - Most important sentences from the article

2015-03-08

In this paper, we propose a novel fitting method that uses local image features to fit a 3D Morphabl… show more
PDF

Highlights - Most important sentences from the article

2017-11-17

We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convo… show more
PDF

Highlights - Most important sentences from the article

2016-10-16

Face recognition performance has improved remarkably in the last decade. Much of this success can be… show more
PDF

Highlights - Most important sentences from the article

2018-01-28
1801.09242 | cs.CV

3D face shape is more expressive and viewpoint-consistent than its 2D counterpart. However, 3D facia… show more
PDF

Highlights - Most important sentences from the article

2019-02-05

Face alignment algorithms locate a set of landmark points in images of faces taken in unrestricted s… show more
PDF

Highlights - Most important sentences from the article

2017-10-02

Estimating the head pose of a person is a crucial problem that has a large amount of applications su… show more
PDF

Highlights - Most important sentences from the article

2016-03-30

Current best local descriptors are learned on a large dataset of matching and non-matching keypoint … show more
PDF

Highlights - Most important sentences from the article

2015-05-27

We present a robust and real-time monocular six degree of freedom relocalization system. Our system … show more
PDF

Highlights - Most important sentences from the article

2018-04-02

Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pix… show more