You're currently viewing an old version of this dataset. To see the current version, click here.

ARText

The ARText dataset contains 33,000 artistic images with rich shape deformation and font diversity, and has been randomly divided into training set (30,000 images) and testing set (3,000 images) for model development.

Data and Resources

Cite this as

Xixuan Hao, Aozhong Zhang, Xianze Meng, Bin Fu (2024). Dataset: ARText. https://doi.org/10.57702/luzcjcxv

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Defined In https://doi.org/10.48550/arXiv.2308.16404
Author Xixuan Hao
More Authors
Aozhong Zhang
Xianze Meng
Bin Fu