liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Towards Controllable Image Generation through Representation-Conditioned Diffusion Models
Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering. (Computer Graphics and Image Processing)ORCID iD: 0000-0003-3476-1986
Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering. (Computer Graphics and Image Processing)ORCID iD: 0000-0002-7765-1747
Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-9217-9997
2025 (English)In: Towards Controllable Image Generation through Representation-Conditioned Diffusion Models, 2025Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

Diffusion models have emerged as powerful tools for high-quality image generation and editing, but guiding these models to produce specific outputs remains a challenge. Conventional approaches rely on conditioning mechanisms, such as text prompts or semantic maps, which require extensively annotated datasets. In this preliminary work, we explore diffusion models conditioned on representations from a pre-trained self-supervised model. The self-conditioning mechanism not only improves the quality of unconditional image generation, but also provides a representation space that can be used to control the generation. We explore this conditioning space by identifying directions of variations, and demonstrate promising properties in terms of smoothness and disentanglement.

Place, publisher, year, edition, pages
2025.
Keywords [en]
Generative Models, Diffusion Models, Representation-Conditioning
National Category
Computer graphics and computer vision
Identifiers
URN: urn:nbn:se:liu:diva-217452OAI: oai:DiVA.org:liu-217452DiVA, id: diva2:1995858
Conference
The 42nd Swedish Symposium on Image Analysis/ The 8th Swedish Symposium on Deep Learning
Available from: 2025-09-08 Created: 2025-09-08 Last updated: 2025-12-19

Open Access in DiVA

No full text in DiVA

Authority records

Karthikeyan, Nithesh ChandherUnger, JonasEilertsen, Gabriel

Search in DiVA

By author/editor
Karthikeyan, Nithesh ChandherUnger, JonasEilertsen, Gabriel
By organisation
Media and Information TechnologyFaculty of Science & Engineering
Computer graphics and computer vision

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 204 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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