This repository shares configured data and augmentation code for BRIND---Berkeley Reflectance, Illuminance, Normal, and Depth edges annotations, which is a dataset for edge detection annotated by @MengyangPu---RINDNet from the BSDS images.

This repository has been released for research and academic purpose. If you need more information about the data that you find here, please, visit the respetive publications. Bellow you will find more details.

• RGB images for the dataset see BSDS.

• Annotation in edge level see RINDNet.

• Details about the GT edge-map preparation and data augmentation see LDC.

If you like BRIND augmentation repo, why not starring the project on GitHub!

If BRIND is helpful in your academic/scientific research, please, cite LDC,

@ARTICLE{xsoria2022ldc,
  author={Soria, Xavier and Pomboza-Junez, Gonzalo and Sappa, Angel Domingo},
  journal={IEEE Access}, 
  title={LDC: Lightweight Dense CNN for Edge Detection}, 
  year={2022},
  volume={10},
  number={},
  pages={68281-68290},
  doi={10.1109/ACCESS.2022.3186344}}

RINDNet publication:

@InProceedings{Pu_2021ICCV_RINDNet,
    author    = {Pu, Mengyang and Huang, Yaping and Guan, Qingji and Ling, Haibin},
    title     = {RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
    pages     = {6879-6888}
}

If you want to contribute in the augmentation of this dataset, please, let me know.