Logo des Repositoriums
 

PictographAI: Interactive Generation of Stylized Pictographs for Presentations

Kurzanzeige
dc.contributor.authorMakarem, Sarah
dc.contributor.authorRöddiger, Tobias
dc.contributor.authorRiedel, Till
dc.contributor.authorBeigl, Michael
dc.date.accessioned2024-08-21T11:08:43Z
dc.date.available2024-08-21T11:08:43Z
dc.date.issued2024
dc.description.abstractIn today’s data-driven world, effective data visualization is crucial for communication. Recent studies have shown that meaningful and relevant visual embellishments and decorations can significantly enhance data visualization memorability and comprehension. Hence, we introduce PictographAI, a generative tool integrated into presentation software to transform traditional bar charts into Pictographic visualizations. Utilizing a multimodal AI pipeline, PictographAI processes text, images, and raw data from presentation slides to automatically generate contextually appropriate pictographs. Our pipeline uses an Large language model agent, a text-guided image-inpainting model, and algorithmic post-processing to make sense of the slide contents and generate pictographs. As users update their presentation slides, the AI pipeline automates the generation of new pictographs that represent the respective contents. In this work, we demonstrate the concept and working principle that motivates the system architecture and the generative AI pipeline on a bar chart generation use case that integrates into a presentation slide creation workflow.en
dc.identifier.doi10.18420/muc2024-mci-demo-305
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/44404
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofMensch und Computer 2024 - Workshopband
dc.relation.ispartofseriesMensch und Computer
dc.rightshttp://purl.org/eprint/accessRights/RestrictedAccess
dc.rights.urihttp://purl.org/eprint/accessRights/RestrictedAccess
dc.subjectpictographs
dc.subjectgenerative AI
dc.subjectLLM agent
dc.subjectinpainting
dc.subjectvisulization
dc.subjectimage generation
dc.subjectpresentations
dc.titlePictographAI: Interactive Generation of Stylized Pictographs for Presentationsen
dc.typeText/Conference Paper
gi.conference.date1.-4. September 2024
gi.conference.locationKarlsruhe
gi.conference.sessiontitleMCI: Demos: Interactive Systems or Demonstrators

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
muc2024-mci-demo-305.pdf
Größe:
2.86 MB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

Workshopband MuC 2024