Diffusion-based Latent Image Generation with Label Conditioning: A Score-Based Approach

Simple item page
dc.contributor.advisorDr. Mohammad Ashrafuzzaman Khan
dc.contributor.authorTawsif Mahmud
dc.contributor.authorJiaul Haque Saboj
dc.contributor.authorSadia Sifati Shammee
dc.contributor.id1912411042
dc.contributor.id1912065042
dc.contributor.id1912304042
dc.coverage.departmentElectrical and Computer Engineering
dc.date.accessioned2025
dc.date.accessioned2025-07-21T04:33:04Z
dc.date.available2025-07-21T04:33:04Z
dc.date.issued2023
dc.description.abstractWe present a novel score-based strategy for image generation using label conditioning, diffusion models, and latent space modeling. By integrating label information into the diffusion models and iteratively revising the latent space with score estimation, our method enables the generation of high-quality images that correspond to specific labels. Through extensive experimentation, we demonstrate that our method is effective at producing realistic images with precise label control and fine-grained details. This score-based method not only provides a flexible framework for label-guided image synthesis, but it also opens up new opportunities in computer vision, artistic design, and creative applications. The combination of label conditioning, diffusion models, and latent space modeling allows us to stretch the limits of image generation and achieve impressive visual outcomes.
dc.description.degreeUndergraduate
dc.identifier.cd600000193
dc.identifier.print-thesisTo be assigned
dc.identifier.urihttps://repository.northsouth.edu/handle/123456789/1294
dc.language.isoen
dc.publisherNorth South University
dc.rights©NSU Library
dc.titleDiffusion-based Latent Image Generation with Label Conditioning: A Score-Based Approach
oaire.citation.endPage37
oaire.citation.startPage1
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
600000193.Abstract.pdf
Size:
97.13 KB
Format:
Adobe Portable Document Format
Description:
Download
Thumbnail Image
Name:
600000193.pdf
Size:
5.44 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.93 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
Theses - Undergraduate