OpenCOLE: Towards Reproducible Automatic Graphic Design Generation

Autor:	Inoue, Naoto, Masui, Kento, Shimoda, Wataru, Yamaguchi, Kota
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Graphics
Druh dokumentu:	Working Paper
Popis:	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. Comment: To appear as an extended abstract (EA) in Workshop on Graphic Design Understanding and Generation (in CVPR2024), code: https://github.com/CyberAgentAILab/OpenCOLE
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2406.08232 Zobrazit plný text záznamu View this record from Arxiv