We propose direction-based super-BPD, an alternative to superpixel, for fast generic image segmentation, achieving state-of-the-art real-time result.

Please cite the related works in your publications if it helps your research:

@InProceedings{Wan_2020_CVPR,
author = {Wan, Jianqiang and Liu, Yang and Wei, Donglai and Bai, Xiang and Xu, Yongchao},
title = {Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}

• pytorch >= 1.3.0
• g++ 7

• Download the BSDS500 & PascalContext Dataset, and unzip it into the Super-BPD/ folder.

• Compile cuda code for post-process.

cd post_process
python setup.py install

• Download the pre-trained PascalContext model and put it in the saved folder.

• Test the model and results will be saved in the test_pred_flux/PascalContext folder.

• SEISM is used for evaluation of image segmentation.

• Download VGG-16 pretrained model.

python train.py --dataset PascalContext