Modelling non-linearity in 3D shapes: A comparative study of Gaussian process morphable models and variational autoencoders for 3D shape data

dc.contributor.advisorClark, Allan
dc.contributor.advisorMutsvangwa, Tinashe
dc.contributor.authorFehr, Fabio
dc.date.accessioned2022-02-18T07:49:24Z
dc.date.available2022-02-18T07:49:24Z
dc.date.issued2021
dc.date.updated2022-02-10T14:59:17Z
dc.description.abstractThe presence of non-linear shape variation in 3D data is known to influence the reliability of linear statistical shape models (SSM). This problem is regularly acknowledged, but disregarded, as it is assumed that linear models are able to adequately approximate such non-linearities. Model reliability is crucial for medical imaging and computer vision tasks; however, prior to modelling, the non-linearity in the data is not often considered. The study provides a framework to identify the presence of non-linearity in using principal component analysis (PCA) and autoencoders (AE) shape modelling methods. The data identified to have linear and non-linear shape variations is used to compare two sophisticated techniques: linear Gaussian process morphable models (GPMM) and non-linear variational autoencoders (VAE). Their model performance is measured using generalisation, specificity and computational efficiency in training. The research showed that, given limited computational power, GPMMs managed to achieve improved relative generalisation performance compared to VAEs, in the presence of non-linear shape variation by at least a factor of six. However, the non-linear VAEs, despite the simplistic training scheme, presented improved specificity generative performance of at least 18% for both datasets.
dc.identifier.apacitationFehr, F. (2021). <i>Modelling non-linearity in 3D shapes: A comparative study of Gaussian process morphable models and variational autoencoders for 3D shape data</i>. (). ,Faculty of Science ,Department of Statistical Sciences. Retrieved from http://hdl.handle.net/11427/35725en_ZA
dc.identifier.chicagocitationFehr, Fabio. <i>"Modelling non-linearity in 3D shapes: A comparative study of Gaussian process morphable models and variational autoencoders for 3D shape data."</i> ., ,Faculty of Science ,Department of Statistical Sciences, 2021. http://hdl.handle.net/11427/35725en_ZA
dc.identifier.citationFehr, F. 2021. Modelling non-linearity in 3D shapes: A comparative study of Gaussian process morphable models and variational autoencoders for 3D shape data. . ,Faculty of Science ,Department of Statistical Sciences. http://hdl.handle.net/11427/35725en_ZA
dc.identifier.ris TY - Master Thesis AU - Fehr, Fabio AB - The presence of non-linear shape variation in 3D data is known to influence the reliability of linear statistical shape models (SSM). This problem is regularly acknowledged, but disregarded, as it is assumed that linear models are able to adequately approximate such non-linearities. Model reliability is crucial for medical imaging and computer vision tasks; however, prior to modelling, the non-linearity in the data is not often considered. The study provides a framework to identify the presence of non-linearity in using principal component analysis (PCA) and autoencoders (AE) shape modelling methods. The data identified to have linear and non-linear shape variations is used to compare two sophisticated techniques: linear Gaussian process morphable models (GPMM) and non-linear variational autoencoders (VAE). Their model performance is measured using generalisation, specificity and computational efficiency in training. The research showed that, given limited computational power, GPMMs managed to achieve improved relative generalisation performance compared to VAEs, in the presence of non-linear shape variation by at least a factor of six. However, the non-linear VAEs, despite the simplistic training scheme, presented improved specificity generative performance of at least 18% for both datasets. DA - 2021_ DB - OpenUCT DP - University of Cape Town KW - Advanced Analytics LK - https://open.uct.ac.za PY - 2021 T1 - Modelling non-linearity in 3D shapes: A comparative study of Gaussian process morphable models and variational autoencoders for 3D shape data TI - Modelling non-linearity in 3D shapes: A comparative study of Gaussian process morphable models and variational autoencoders for 3D shape data UR - http://hdl.handle.net/11427/35725 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/35725
dc.identifier.vancouvercitationFehr F. Modelling non-linearity in 3D shapes: A comparative study of Gaussian process morphable models and variational autoencoders for 3D shape data. []. ,Faculty of Science ,Department of Statistical Sciences, 2021 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/35725en_ZA
dc.language.rfc3066eng
dc.publisher.departmentDepartment of Statistical Sciences
dc.publisher.facultyFaculty of Science
dc.subjectAdvanced Analytics
dc.titleModelling non-linearity in 3D shapes: A comparative study of Gaussian process morphable models and variational autoencoders for 3D shape data
dc.typeMaster Thesis
dc.type.qualificationlevelMasters
dc.type.qualificationlevelMSc
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_sci_2021_fehr fabio.pdf
Size:
15.2 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
0 B
Format:
Item-specific license agreed upon to submission
Description:
Collections