Matches in SemOpenAlex for { <https://semopenalex.org/work/W4303439004> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4303439004 abstract "Research in vision-language models has seen rapid developments off-late, enabling natural language-based interfaces for image generation and manipulation. Many existing text guided manipulation techniques are restricted to specific classes of images, and often require fine-tuning to transfer to a different style or domain. Nevertheless, generic image manipulation using a single model with flexible text inputs is highly desirable. Recent work addresses this task by guiding generative models trained on the generic image datasets using pretrained vision-language encoders. While promising, this approach requires expensive optimization for each input. In this work, we propose an optimization-free method for the task of generic image manipulation from text prompts. Our approach exploits recent Latent Diffusion Models (LDM) for text to image generation to achieve zero-shot text guided manipulation. We employ a deterministic forward diffusion in a lower dimensional latent space, and the desired manipulation is achieved by simply providing the target text to condition the reverse diffusion process. We refer to our approach as LDEdit. We demonstrate the applicability of our method on semantic image manipulation and artistic style transfer. Our method can accomplish image manipulation on diverse domains and enables editing multiple attributes in a straightforward fashion. Extensive experiments demonstrate the benefit of our approach over competing baselines." @default.
- W4303439004 created "2022-10-07" @default.
- W4303439004 creator A5048073110 @default.
- W4303439004 creator A5063240708 @default.
- W4303439004 date "2022-10-05" @default.
- W4303439004 modified "2023-09-30" @default.
- W4303439004 title "LDEdit: Towards Generalized Text Guided Image Manipulation via Latent Diffusion Models" @default.
- W4303439004 doi "https://doi.org/10.48550/arxiv.2210.02249" @default.
- W4303439004 hasPublicationYear "2022" @default.
- W4303439004 type Work @default.
- W4303439004 citedByCount "0" @default.
- W4303439004 crossrefType "posted-content" @default.
- W4303439004 hasAuthorship W4303439004A5048073110 @default.
- W4303439004 hasAuthorship W4303439004A5063240708 @default.
- W4303439004 hasBestOaLocation W43034390041 @default.
- W4303439004 hasConcept C111919701 @default.
- W4303439004 hasConcept C115961682 @default.
- W4303439004 hasConcept C118505674 @default.
- W4303439004 hasConcept C134306372 @default.
- W4303439004 hasConcept C137293760 @default.
- W4303439004 hasConcept C154945302 @default.
- W4303439004 hasConcept C162324750 @default.
- W4303439004 hasConcept C167966045 @default.
- W4303439004 hasConcept C187736073 @default.
- W4303439004 hasConcept C2776674983 @default.
- W4303439004 hasConcept C2780451532 @default.
- W4303439004 hasConcept C31972630 @default.
- W4303439004 hasConcept C33923547 @default.
- W4303439004 hasConcept C36503486 @default.
- W4303439004 hasConcept C39890363 @default.
- W4303439004 hasConcept C41008148 @default.
- W4303439004 hasConceptScore W4303439004C111919701 @default.
- W4303439004 hasConceptScore W4303439004C115961682 @default.
- W4303439004 hasConceptScore W4303439004C118505674 @default.
- W4303439004 hasConceptScore W4303439004C134306372 @default.
- W4303439004 hasConceptScore W4303439004C137293760 @default.
- W4303439004 hasConceptScore W4303439004C154945302 @default.
- W4303439004 hasConceptScore W4303439004C162324750 @default.
- W4303439004 hasConceptScore W4303439004C167966045 @default.
- W4303439004 hasConceptScore W4303439004C187736073 @default.
- W4303439004 hasConceptScore W4303439004C2776674983 @default.
- W4303439004 hasConceptScore W4303439004C2780451532 @default.
- W4303439004 hasConceptScore W4303439004C31972630 @default.
- W4303439004 hasConceptScore W4303439004C33923547 @default.
- W4303439004 hasConceptScore W4303439004C36503486 @default.
- W4303439004 hasConceptScore W4303439004C39890363 @default.
- W4303439004 hasConceptScore W4303439004C41008148 @default.
- W4303439004 hasLocation W43034390041 @default.
- W4303439004 hasOpenAccess W4303439004 @default.
- W4303439004 hasPrimaryLocation W43034390041 @default.
- W4303439004 hasRelatedWork W2092957489 @default.
- W4303439004 hasRelatedWork W2902238479 @default.
- W4303439004 hasRelatedWork W2904276469 @default.
- W4303439004 hasRelatedWork W2951021768 @default.
- W4303439004 hasRelatedWork W2951647648 @default.
- W4303439004 hasRelatedWork W3184956571 @default.
- W4303439004 hasRelatedWork W3204120495 @default.
- W4303439004 hasRelatedWork W3205181580 @default.
- W4303439004 hasRelatedWork W4319453795 @default.
- W4303439004 hasRelatedWork W4378942371 @default.
- W4303439004 isParatext "false" @default.
- W4303439004 isRetracted "false" @default.
- W4303439004 workType "article" @default.