CreativeConnect
Supporting Reference Recombination for Graphic Design Ideation with Generative AI
Designers often get a new idea by recombining the existing design ideas. CreativeConnect is a generative AI system that helps graphic designers' early-stage ideation process by supporting reference recombination. It helps users discover useful elements from the reference image using keywords, recommends relevant keywords, generates diverse recombination options with user-selected keywords, and shows recombinations as sketches with text descriptions.
System Interface
CreativeConnect consists of a mood board where users can import reference images, and three panels that support reference recombination.
Keyword Extraction Panel helps users discover useful elements from the reference image. When users import a reference image into the mood board, the system extracts keywords based on four categories: (1) Subject matter, (2) Action & pose, (3) Theme & Mood, and (4) Arrangement.
Keyword Suggestion Panel recommends relevant keywords based on the extracted keywords. The system recommends similar keywords based on both (1) all keywords on the mood board and (2) the selected keywords.
Recombination Panel generates diverse recombination options with user-selected keywords, and shows recombinations as sketches with text descriptions. When the user selects keywords and clicks the merge button, the system generates three recombination options. The recombined results are first shown as one-line text descriptions, and the sketch is generated based on them. Users can also click the "More sketches" button to get more sketches with the same text description.
Video Figure
Abstract
Graphic designers often get inspiration through the recombination of references. Our formative study (N=6) reveals that graphic designers focus on conceptual keywords during this process, and want support for discovering the keywords, expanding them, and exploring diverse recombination options of them, while still having room for their creativity. We propose CreativeConnect, a system with generative AI pipelines that helps users discover useful elements from the reference image using keywords, recommends relevant keywords, generates diverse recombination options with user-selected keywords, and shows recombinations as sketches with text descriptions. Our user study (N=16) showed that CreativeConnect helped users discover keywords from the reference and generate multiple ideas based on them, ultimately helping users produce more design ideas and higher self-reported creativity, compared to the baseline system without generative pipelines. While CreativeConnect was effective in ideation, we discussed how CreativeConnect can be extended to support other types of tasks in creativity support.
Bibtex
@inproceedings{10.1145/3613904.3642794,
author = {Choi, DaEun and Hong, Sumin and Park, Jeongeon and Chung, John Joon Young and Kim, Juho},
title = {CreativeConnect: Supporting Reference Recombination for Graphic Design Ideation with Generative AI},
year = {2024},
isbn = {9798400703300},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3613904.3642794},
doi = {10.1145/3613904.3642794},
booktitle = {Proceedings of the CHI Conference on Human Factors in Computing Systems},
articleno = {1055},
numpages = {25},
location = {Honolulu, HI, USA},
series = {CHI '24}
}