IRUS Total

Advances in generative modelling: from component analysis to generative adversarial networks

File Description SizeFormat 
Moschoglou-S-2021-PhD-Thesis.pdfThesis45.43 MBAdobe PDFView/Open
Title: Advances in generative modelling: from component analysis to generative adversarial networks
Authors: Moschoglou, Stylianos
Item Type: Thesis or dissertation
Abstract: This Thesis revolves around datasets and algorithms, with a focus on generative modelling. In particular, we first turn our attention to a novel, multi-attribute, 2D facial dataset. We then present deterministic as well as probabilistic Component Analysis (CA) techniques which can be applied to multi-attribute 2D as well as 3D data. We finally present deep learning generative approaches specially designed to manipulate 3D facial data. Most 2D facial datasets that are available in the literature, are: a) automatically or semi-automatically collected and thus contain noisy labels, hindering the benchmarking and comparisons between algorithms. Moreover, they are not annotated for multiple attributes. In the first part of the Thesis, we present the first manually collected and annotated database, which contains labels for multiple attributes. As we demonstrate in a series of experiments, it can be used in a number of applications ranging from image translation to age-invariant face recognition. Moving on, we turn our attention to CA methodologies. CA approaches, although being able to only capture linear relationships between data, can still be proven to be efficient in data such as UV maps or 3D data registered in a common template, since they are well aligned. The introduction of more complex datasets in the literature, which contain labels for multiple attributes, naturally brought the need for novel algorithms that can simultaneously handle multiple attributes. In this Thesis, we cover novel CA approaches which are specifically designed to be utilised in datasets annotated with respect to multiple attributes and can be used in a variety of tasks, such as 2D image denoising and translation, as well as 3D data generation and identification. Nevertheless, while CA methods are indeed efficient when handling registered 3D facial data, linear 3D generative models lack details when it comes to reconstructing or generating finer facial characteristics. To alleviate this, in the final part of this Thesis we propose a novel generative framework harnessing the power of Generative Adversarial Networks.
Content Version: Open Access
Issue Date: Oct-2020
Date Awarded: Jul-2021
URI: http://hdl.handle.net/10044/1/91694
DOI: https://doi.org/10.25560/91694
Copyright Statement: Creative Commons Attribution NonCommercial Licence
Supervisor: Zafeiriou, Stefanos
Sponsor/Funder: Imperial College of London
Funder's Grant Number: EP/N509486/1
Department: Computing
Publisher: Imperial College London
Qualification Level: Doctoral
Qualification Name: Doctor of Philosophy (PhD)
Appears in Collections:Computing PhD theses

This item is licensed under a Creative Commons License Creative Commons