Dataset Card for RefEdit

Dataset Summary

The training dataset covers a synthetically generated ~20K editing triplets on changing color, changing object, adding an object, removing an object and changing texture.

Dataset Structure

"img_id" (str): unique id

"source_img" (str): the original image generated using FLUX

"instruction" (str): edit instruction of how the input image should be changed.

"target_img" (str): the edited image corresponding to the input image and instruction.

Citation

If you use this code or the dataset in your research, please cite our paper:

@article{pathiraja2023refedit,
  title={RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model for Referring Expression},
  author={Pathiraja, Bimsara and Patel, Maitreya and Singh, Shivam and Yang, Yezhou and Baral, Chitta},
  journal={arXiv preprint arXiv:2309.12345},
  year={2025}
}