Fulltext available Open Access
License: 
Title: Stochastic optimization of synthetic data for neural net based 3d face synthesis
Language: English
Authors: Scholz, Jan
Keywords: generative modelling; deep neural networks; generative adversarial network; gaussian mixture model; regression; principal component analysis
Issue Date: 9-Apr-2019
Abstract: 
In dieser Arbeit wird das Basel Face Model 2017 (BFM) im Hinblick auf die Generierung von Lerndaten für Regressions-Netze untersucht. Ein Regressions-Netz wird erstellt das aus Eingabebildern von Gesichtern Parametervektoren für das BFM erstellt. Diese Parametervektoren sind eine vergleichsweise nierdig dimensionale Repräsentation von Gesichtern die dann in einem nächsten Schritt als Pointcloud od...

In this work, the Basel Face Model 2017 (BFM) will be examined with regard to the generation of learning data for a regression network. A regression network is created that infers parameter vectors for the BFM from input images of faces. These parameter vectors are a comparably low dimensional representation of faces which can then be provided in a next step as point cloud or mesh. The regression ...
URI: http://hdl.handle.net/20.500.12738/8653
Institute: Department Informatik 
Type: Thesis
Thesis type: Master Thesis
Advisor: Meisel, Andreas 
Referee: Jenke, Philipp 
Appears in Collections:Theses

Files in This Item:
File Description SizeFormat
Master_Arbeit_vektor.pdf23.47 MBAdobe PDFView/Open
Show full item record

Page view(s)

115
checked on Apr 6, 2025

Download(s)

75
checked on Apr 6, 2025

Google ScholarTM

Check

HAW Katalog

Check

Note about this record


Items in REPOSIT are protected by copyright, with all rights reserved, unless otherwise indicated.