TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915590427377664 |
|---|---|
| author | Wang, Alex Jinpeng Mao, Dongxing Zhang, Jiawei Han, Weiming Dong, Zhuobai Li, Linjie Lin, Yiqi Yang, Zhengyuan Qin, Libo Zhang, Fuwei Wang, Lijuan Li, Min |
| author_facet | Wang, Alex Jinpeng Mao, Dongxing Zhang, Jiawei Han, Weiming Dong, Zhuobai Li, Linjie Lin, Yiqi Yang, Zhengyuan Qin, Libo Zhang, Fuwei Wang, Lijuan Li, Min |
| contents | Text-conditioned image generation has gained significant attention in recent years and are processing increasingly longer and comprehensive text prompt. In everyday life, dense and intricate text appears in contexts like advertisements, infographics, and signage, where the integration of both text and visuals is essential for conveying complex information. However, despite these advances, the generation of images containing long-form text remains a persistent challenge, largely due to the limitations of existing datasets, which often focus on shorter and simpler text. To address this gap, we introduce TextAtlas5M, a novel dataset specifically designed to evaluate long-text rendering in text-conditioned image generation. Our dataset consists of 5 million long-text generated and collected images across diverse data types, enabling comprehensive evaluation of large-scale generative models on long-text image generation. We further curate 3000 human-improved test set TextAtlasEval across 3 data domains, establishing one of the most extensive benchmarks for text-conditioned generation. Evaluations suggest that the TextAtlasEval benchmarks present significant challenges even for the most advanced proprietary models (e.g. GPT4o with DallE-3), while their open-source counterparts show an even larger performance gap. These evidences position TextAtlas5M as a valuable dataset for training and evaluating future-generation text-conditioned image generation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_07870 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation Wang, Alex Jinpeng Mao, Dongxing Zhang, Jiawei Han, Weiming Dong, Zhuobai Li, Linjie Lin, Yiqi Yang, Zhengyuan Qin, Libo Zhang, Fuwei Wang, Lijuan Li, Min Computer Vision and Pattern Recognition Text-conditioned image generation has gained significant attention in recent years and are processing increasingly longer and comprehensive text prompt. In everyday life, dense and intricate text appears in contexts like advertisements, infographics, and signage, where the integration of both text and visuals is essential for conveying complex information. However, despite these advances, the generation of images containing long-form text remains a persistent challenge, largely due to the limitations of existing datasets, which often focus on shorter and simpler text. To address this gap, we introduce TextAtlas5M, a novel dataset specifically designed to evaluate long-text rendering in text-conditioned image generation. Our dataset consists of 5 million long-text generated and collected images across diverse data types, enabling comprehensive evaluation of large-scale generative models on long-text image generation. We further curate 3000 human-improved test set TextAtlasEval across 3 data domains, establishing one of the most extensive benchmarks for text-conditioned generation. Evaluations suggest that the TextAtlasEval benchmarks present significant challenges even for the most advanced proprietary models (e.g. GPT4o with DallE-3), while their open-source counterparts show an even larger performance gap. These evidences position TextAtlas5M as a valuable dataset for training and evaluating future-generation text-conditioned image generation models. |
| title | TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.07870 |