kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Using a Deep Generative Model to Generate and Manipulate 3D Object Representation
KTH, School of Electrical Engineering and Computer Science (EECS).
2023 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Att använda en djup generativ modell för att skapa och manipulera 3D-objektrepresentation. (Swedish)
Abstract [en]

The increasing importance of 3D data in various domains, such as computer vision, robotics, medical analysis, augmented reality, and virtual reality, has gained giant research interest in generating 3D data using deep generative models. The challenging problem is how to build generative models to synthesize diverse and realistic 3D objects representations, while having controllability for manipulating the shape attributes of 3D objects. This thesis explores the use of 3D Generative Adversarial Networks (GANs) for generation of 3D indoor objects shapes represented by point clouds, with a focus on shape editing tasks. Leveraging insights from 2D semantic face editing, the thesis proposes extending the InterFaceGAN framework to 3D GAN model for discovering the relationship between latent codes and semantic attributes of generated shapes. In the end, we successfully perform controllable shape editing by manipulating the latent code of GAN.

Abstract [sv]

Den ökande betydelsen av 3D-data inom olika områden, såsom datorseende, robotik, medicinsk analys, förstärkt verklighet och virtuell verklighet, har väckt stort forskningsintresse för att generera 3D-data med hjälp av djupa generativa modeller. Det utmanande problemet är hur man bygger generativa modeller för att syntetisera varierande och realistiska 3Dobjektrepresentationer samtidigt som man har kontroll över att manipulera formattributen hos 3D-objekt. Denna avhandling utforskar användningen av 3D Generative Adversarial Networks (GANs) för generering av 3Dinomhusobjektformer representerade av punktmoln, med fokus på formredigeringsuppgifter. Genom att dra nytta av insikter från 2D-semantisk ansiktsredigering föreslår avhandlingen att utvidga InterFaceGAN-ramverket till en 3D GAN-modell för att upptäcka förhållandet mellan latenta koder och semantiska egenskaper hos genererade former. I slutändan genomför vi framgångsrikt kontrollerad formredigering genom att manipulera den latenta koden hos GAN.

Place, publisher, year, edition, pages
2023. , p. 49
Series
TRITA-EECS-EX ; 2023:889
Keywords [en]
Neural networks, point cloud, 3D shape generation, 3D shape manipulation, classification
Keywords [sv]
Neurala nätverk, punktmoln, generering av 3D-former, manipulation av 3Dformer, klassificering
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-343459OAI: oai:DiVA.org:kth-343459DiVA, id: diva2:1837778
Educational program
Master of Science - Machine Learning
Supervisors
Examiners
Available from: 2024-02-15 Created: 2024-02-14 Last updated: 2024-02-15Bibliographically approved

Open Access in DiVA

fulltext(6149 kB)468 downloads
File information
File name FULLTEXT01.pdfFile size 6149 kBChecksum SHA-512
e075c12305568a622646d3311c73cb5a21e36775cd0f298d32fdffdc44f2aa91f9c269a9f26ba6790ac304c9a4fd27aabcfae743735d4b909507d0050c956f7f
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 468 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 248 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf