Generative Models for Neural Fields

Simple item page
dc.contributor.advisorWonka, Peter
dc.contributor.advisorElhoseiny, Mohamed
dc.contributor.authorSkorokhodov, Ivan
dc.contributor.committeememberGhanem, Bernard
dc.contributor.committeememberHeidrich, Wolfgang
dc.contributor.committeememberNiessner, Matthias
dc.contributor.departmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
dc.date.accessioned2023-03-19T11:45:52Z
dc.date.available2023-03-19T11:45:52Z
dc.date.issued2023-02
dc.description.abstractDeep generative models are deep learning-based methods that are optimized to synthesize samples of a given distribution. During the past years, they have attracted a lot of interest from the research community, and the developed tools now enjoy many practical applications in content creation and editing. In computer vision, such models are typically built for images, videos, and 3D objects. Recently, there has emerged a paradigm of neural fields, which unifies the representations of such types of data by parametrizing them via neural networks. In this work, we develop generative modeling methods for images, videos, and 3D objects which treat the underlying data in such a form. We show that this perspective can yield state-of-the-art synthesis quality and many useful practical benefits, like interpolation/extrapolation capabilities, geometric inductive biases, and more efficient training and inference.
dc.identifier.citationSkorokhodov, I. (2023). Generative Models for Neural Fields [KAUST Research Repository]. https://doi.org/10.25781/KAUST-54DV8
dc.identifier.doi10.25781/KAUST-54DV8
dc.identifier.orcid0000-0002-7611-9310
dc.identifier.urihttp://hdl.handle.net/10754/690419
dc.language.isoen
dc.person.id176005
dc.relation.issupplementedbyN/A
dc.subjectgenerative models
dc.subjectneural fields
dc.subjectgenerative AI
dc.subjectgenerative adversarial networks
dc.subjectgans
dc.subjectimage generation
dc.subjectvideo generation
dc.subject3D generation
dc.subjectimage synthesis
dc.subjectvideo synthesis
dc.subject3D synthesis
dc.titleGenerative Models for Neural Fields
dc.typeDissertation
display.details.left<span><h5>Type</h5>Dissertation<br><br><h5>Authors</h5><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0002-7611-9310&spc.sf=dc.date.issued&spc.sd=DESC">Skorokhodov, Ivan</a> <a href="https://orcid.org/0000-0002-7611-9310" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><br><h5>Advisors</h5><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0003-0627-9746&spc.sf=dc.date.issued&spc.sd=DESC">Wonka, Peter</a> <a href="https://orcid.org/0000-0003-0627-9746" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0001-9659-1551&spc.sf=dc.date.issued&spc.sd=DESC">Elhoseiny, Mohamed</a> <a href="https://orcid.org/0000-0001-9659-1551" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><br><h5>Committee Members</h5><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0002-5534-587X&spc.sf=dc.date.issued&spc.sd=DESC">Ghanem, Bernard</a> <a href="https://orcid.org/0000-0002-5534-587X" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0002-4227-8508&spc.sf=dc.date.issued&spc.sd=DESC">Heidrich, Wolfgang</a> <a href="https://orcid.org/0000-0002-4227-8508" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br>Niessner, Matthias<br><br><h5>Program</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.program=Computer Science,equals">Computer Science</a><br><br><h5>KAUST Department</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division,equals">Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division</a><br><br><h5>Date</h5>2023-02</span>
display.details.right<span><h5>Abstract</h5>Deep generative models are deep learning-based methods that are optimized to synthesize samples of a given distribution. During the past years, they have attracted a lot of interest from the research community, and the developed tools now enjoy many practical applications in content creation and editing. In computer vision, such models are typically built for images, videos, and 3D objects. Recently, there has emerged a paradigm of neural fields, which unifies the representations of such types of data by parametrizing them via neural networks. In this work, we develop generative modeling methods for images, videos, and 3D objects which treat the underlying data in such a form. We show that this perspective can yield state-of-the-art synthesis quality and many useful practical benefits, like interpolation/extrapolation capabilities, geometric inductive biases, and more efficient training and inference.<br><br><h5>Citation</h5>Skorokhodov, I. (2023). Generative Models for Neural Fields [KAUST Research Repository]. https://doi.org/10.25781/KAUST-54DV8<br><br><h5>DOI</h5><a href="https://doi.org/10.25781/KAUST-54DV8">10.25781/KAUST-54DV8</a></span>
kaust.availability.selectionRelease the work immediately for public access* on the internet through the KAUST Repository.
kaust.gpcaida.hoteit@kaust.edu.sa
kaust.request.doiyes
kaust.thesis.readyToSubmitYes, I confirm that I am ready to upload the following 3 documents (in PDF format): 1) Final thesis or dissertation. 2) Completed Defense Results form showing “pass” or “pass with conditions”. 3) Final Advisor Approval confirmation email (received after advisor completed the digital form).
orcid.id0000-0002-4227-8508
orcid.id0000-0002-5534-587X
orcid.id0000-0001-9659-1551
orcid.id0000-0003-0627-9746
orcid.id0000-0002-7611-9310
refterms.dateFOA2023-03-19T11:45:53Z
thesis.degree.disciplineComputer Science
thesis.degree.grantorKing Abdullah University of Science and Technology
thesis.degree.nameDoctor of Philosophy
Files
Original bundle
Now showing 1 - 3 of 3
Name:
Ivan Skorokhdov - thesis-result-form signed.pdf
Size:
523.49 KB
Format:
Adobe Portable Document Format
Description:
PhD defense results form
Download
Name:
approval-form-screenshot.png
Size:
267.24 KB
Format:
Portable Network Graphics
Description:
Approval form screenshot
Download
Thumbnail Image
Name:
Generative Models for Neural Fields.pdf
Size:
64.79 MB
Format:
Adobe Portable Document Format
Description:
Generative Models for Neural Fields - PhD thesis
Download
License bundle
Now showing 1 - 1 of 1
Name:
license.txt
Size:
919 B
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
PhD Dissertations
Computer Science Program
Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division