OpenCOLE: Towards Reproducible Automatic Graphic Design Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911914489020416 |
|---|---|
| author | Inoue, Naoto Masui, Kento Shimoda, Wataru Yamaguchi, Kota |
| author_facet | Inoue, Naoto Masui, Kento Shimoda, Wataru Yamaguchi, Kota |
| contents | Automatic generation of graphic designs has recently received considerable attention. However, the state-of-the-art approaches are complex and rely on proprietary datasets, which creates reproducibility barriers. In this paper, we propose an open framework for automatic graphic design called OpenCOLE, where we build a modified version of the pioneering COLE and train our model exclusively on publicly available datasets. Based on GPT4V evaluations, our model shows promising performance comparable to the original COLE. We release the pipeline and training results to encourage open development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08232 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OpenCOLE: Towards Reproducible Automatic Graphic Design Generation Inoue, Naoto Masui, Kento Shimoda, Wataru Yamaguchi, Kota Computer Vision and Pattern Recognition Graphics Automatic generation of graphic designs has recently received considerable attention. However, the state-of-the-art approaches are complex and rely on proprietary datasets, which creates reproducibility barriers. In this paper, we propose an open framework for automatic graphic design called OpenCOLE, where we build a modified version of the pioneering COLE and train our model exclusively on publicly available datasets. Based on GPT4V evaluations, our model shows promising performance comparable to the original COLE. We release the pipeline and training results to encourage open development. |
| title | OpenCOLE: Towards Reproducible Automatic Graphic Design Generation |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2406.08232 |