Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221163505> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4221163505 abstract "Generating images that fit a given text description using machine learning has improved greatly with the release of technologies such as the CLIP image-text encoder model; however, current methods lack artistic control of the style of image to be generated. We present an approach for generating styled drawings for a given text description where a user can specify a desired drawing style using a sample image. Inspired by a theory in art that style and content are generally inseparable during the creative process, we propose a coupled approach, known here as StyleCLIPDraw, whereby the drawing is generated by optimizing for style and content simultaneously throughout the process as opposed to applying style transfer after creating content in a sequence. Based on human evaluation, the styles of images generated by StyleCLIPDraw are strongly preferred to those by the sequential approach. Although the quality of content generation degrades for certain styles, overall considering both content textit{and} style, StyleCLIPDraw is found far more preferred, indicating the importance of style, look, and feel of machine generated images to people as well as indicating that style is coupled in the drawing process itself. Our code (https://github.com/pschaldenbrand/StyleCLIPDraw), a demonstration (https://replicate.com/pschaldenbrand/style-clip-draw), and style evaluation data (https://www.kaggle.com/pittsburghskeet/drawings-with-style-evaluation-styleclipdraw) are publicly available." @default.
- W4221163505 created "2022-04-03" @default.
- W4221163505 creator A5019807694 @default.
- W4221163505 creator A5047422379 @default.
- W4221163505 creator A5064261982 @default.
- W4221163505 date "2022-02-24" @default.
- W4221163505 modified "2023-09-29" @default.
- W4221163505 title "StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Translation" @default.
- W4221163505 doi "https://doi.org/10.48550/arxiv.2202.12362" @default.
- W4221163505 hasPublicationYear "2022" @default.
- W4221163505 type Work @default.
- W4221163505 citedByCount "1" @default.
- W4221163505 countsByYear W42211635052023 @default.
- W4221163505 crossrefType "posted-content" @default.
- W4221163505 hasAuthorship W4221163505A5019807694 @default.
- W4221163505 hasAuthorship W4221163505A5047422379 @default.
- W4221163505 hasAuthorship W4221163505A5064261982 @default.
- W4221163505 hasBestOaLocation W42211635051 @default.
- W4221163505 hasConcept C105795698 @default.
- W4221163505 hasConcept C111472728 @default.
- W4221163505 hasConcept C111919701 @default.
- W4221163505 hasConcept C115961682 @default.
- W4221163505 hasConcept C118505674 @default.
- W4221163505 hasConcept C134306372 @default.
- W4221163505 hasConcept C138885662 @default.
- W4221163505 hasConcept C142362112 @default.
- W4221163505 hasConcept C153349607 @default.
- W4221163505 hasConcept C154945302 @default.
- W4221163505 hasConcept C177264268 @default.
- W4221163505 hasConcept C199360897 @default.
- W4221163505 hasConcept C204321447 @default.
- W4221163505 hasConcept C23123220 @default.
- W4221163505 hasConcept C2776445246 @default.
- W4221163505 hasConcept C2776760102 @default.
- W4221163505 hasConcept C2778152352 @default.
- W4221163505 hasConcept C2779530757 @default.
- W4221163505 hasConcept C2781162219 @default.
- W4221163505 hasConcept C33923547 @default.
- W4221163505 hasConcept C41008148 @default.
- W4221163505 hasConcept C98045186 @default.
- W4221163505 hasConceptScore W4221163505C105795698 @default.
- W4221163505 hasConceptScore W4221163505C111472728 @default.
- W4221163505 hasConceptScore W4221163505C111919701 @default.
- W4221163505 hasConceptScore W4221163505C115961682 @default.
- W4221163505 hasConceptScore W4221163505C118505674 @default.
- W4221163505 hasConceptScore W4221163505C134306372 @default.
- W4221163505 hasConceptScore W4221163505C138885662 @default.
- W4221163505 hasConceptScore W4221163505C142362112 @default.
- W4221163505 hasConceptScore W4221163505C153349607 @default.
- W4221163505 hasConceptScore W4221163505C154945302 @default.
- W4221163505 hasConceptScore W4221163505C177264268 @default.
- W4221163505 hasConceptScore W4221163505C199360897 @default.
- W4221163505 hasConceptScore W4221163505C204321447 @default.
- W4221163505 hasConceptScore W4221163505C23123220 @default.
- W4221163505 hasConceptScore W4221163505C2776445246 @default.
- W4221163505 hasConceptScore W4221163505C2776760102 @default.
- W4221163505 hasConceptScore W4221163505C2778152352 @default.
- W4221163505 hasConceptScore W4221163505C2779530757 @default.
- W4221163505 hasConceptScore W4221163505C2781162219 @default.
- W4221163505 hasConceptScore W4221163505C33923547 @default.
- W4221163505 hasConceptScore W4221163505C41008148 @default.
- W4221163505 hasConceptScore W4221163505C98045186 @default.
- W4221163505 hasLocation W42211635051 @default.
- W4221163505 hasOpenAccess W4221163505 @default.
- W4221163505 hasPrimaryLocation W42211635051 @default.
- W4221163505 hasRelatedWork W1495877081 @default.
- W4221163505 hasRelatedWork W1511492033 @default.
- W4221163505 hasRelatedWork W2036641180 @default.
- W4221163505 hasRelatedWork W2356875448 @default.
- W4221163505 hasRelatedWork W2755815084 @default.
- W4221163505 hasRelatedWork W2918156780 @default.
- W4221163505 hasRelatedWork W3033962221 @default.
- W4221163505 hasRelatedWork W3107474891 @default.
- W4221163505 hasRelatedWork W9662544 @default.
- W4221163505 hasRelatedWork W2111002739 @default.
- W4221163505 isParatext "false" @default.
- W4221163505 isRetracted "false" @default.
- W4221163505 workType "article" @default.