Deep learning for real world face alignment

Face alignment is one of the fundamental steps in a vast number of tasks of high economical and social value, ranging from security to health and entertainment. Despite the attention received from the community for more than 2 decades and the success of cascaded regression based approaches, many cha...

Full description

Bibliographic Details
Main Author: Bulat, Adrian
Format: Thesis (University of Nottingham only)
Language:English
Published: 2019
Subjects:
Online Access:https://eprints.nottingham.ac.uk/56145/
_version_ 1848799278788509696
author Bulat, Adrian
author_facet Bulat, Adrian
author_sort Bulat, Adrian
building Nottingham Research Data Repository
collection Online Access
description Face alignment is one of the fundamental steps in a vast number of tasks of high economical and social value, ranging from security to health and entertainment. Despite the attention received from the community for more than 2 decades and the success of cascaded regression based approaches, many challenges were yet to be solved, such as the case of near-profile poses and low resolution faces. In this thesis, we successfully address a series of such challenges in the area of face alignment and super-resolution, significantly pushing the state-of-the-art by proposing novel deep learning-based architectures specially tailored for fine grained recognition tasks. In summary, we address the following problems: (I) fitting faces found in large poses (Chapter 3), (II) in both 2D and 3D space (Chapter 4), creating in the process (III) the largest in-the-wild large pose 3D face alignment dataset (Chapter 4). While the case of high resolution faces was actively explored in the past, in this thesis we systematically study and address a new challenge: that of (IV) fitting landmarks in very low resolution faces (Chapter 6). While deep learning based approaches achieved remarkable results on a wide variety of tasks, they are usually slow having high computational requirements. As such, in Chapter 5, we propose (V) a novel residual block carefully crafted for binarized neural networks that significantly improves the speed, due to the use of binary operations for both the weights and the activations, while maintaining a similar or competitive accuracy. The results presented through out this thesis set the new state-of-the-art on both 2D & 3D face alignment and face super-resolution.
first_indexed 2025-11-14T20:33:08Z
format Thesis (University of Nottingham only)
id nottingham-56145
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:33:08Z
publishDate 2019
recordtype eprints
repository_type Digital Repository
spelling nottingham-561452025-02-28T12:10:57Z https://eprints.nottingham.ac.uk/56145/ Deep learning for real world face alignment Bulat, Adrian Face alignment is one of the fundamental steps in a vast number of tasks of high economical and social value, ranging from security to health and entertainment. Despite the attention received from the community for more than 2 decades and the success of cascaded regression based approaches, many challenges were yet to be solved, such as the case of near-profile poses and low resolution faces. In this thesis, we successfully address a series of such challenges in the area of face alignment and super-resolution, significantly pushing the state-of-the-art by proposing novel deep learning-based architectures specially tailored for fine grained recognition tasks. In summary, we address the following problems: (I) fitting faces found in large poses (Chapter 3), (II) in both 2D and 3D space (Chapter 4), creating in the process (III) the largest in-the-wild large pose 3D face alignment dataset (Chapter 4). While the case of high resolution faces was actively explored in the past, in this thesis we systematically study and address a new challenge: that of (IV) fitting landmarks in very low resolution faces (Chapter 6). While deep learning based approaches achieved remarkable results on a wide variety of tasks, they are usually slow having high computational requirements. As such, in Chapter 5, we propose (V) a novel residual block carefully crafted for binarized neural networks that significantly improves the speed, due to the use of binary operations for both the weights and the activations, while maintaining a similar or competitive accuracy. The results presented through out this thesis set the new state-of-the-art on both 2D & 3D face alignment and face super-resolution. 2019-07-24 Thesis (University of Nottingham only) NonPeerReviewed application/pdf en arr https://eprints.nottingham.ac.uk/56145/1/thesis_ab.pdf Bulat, Adrian (2019) Deep learning for real world face alignment. PhD thesis, University of Nottingham. computer vision face alignment
spellingShingle computer vision
face alignment
Bulat, Adrian
Deep learning for real world face alignment
title Deep learning for real world face alignment
title_full Deep learning for real world face alignment
title_fullStr Deep learning for real world face alignment
title_full_unstemmed Deep learning for real world face alignment
title_short Deep learning for real world face alignment
title_sort deep learning for real world face alignment
topic computer vision
face alignment
url https://eprints.nottingham.ac.uk/56145/