yun-liu/RCF-Jittor

Richer Convolutional Features for Edge Detection

This is the Jittor implementation of our edge detection method, RCF.

Citations

If you are using the code/model/data provided here in a publication, please consider citing:

@article{liu2019richer,
  title={Richer Convolutional Features for Edge Detection},
  author={Liu, Yun and Cheng, Ming-Ming and Hu, Xiaowei and Bian, Jia-Wang and Zhang, Le and Bai, Xiang and Tang, Jinhui},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={41},
  number={8},
  pages={1939--1946},
  year={2019},
  publisher={IEEE}
}

Requirements

Jittor
PyTorch (just for loading the pretrained model)
numpy
opencv-python
scipy

Testing

Clone the RCF repository:

git clone https://github.com/yun-liu/RCF-Jittor.git

Download the pretrained model (BSDS500+PASCAL), and put it into the $ROOT_DIR folder.
Download the BSDS500 dataset as below, and extract it to the $ROOT_DIR/data/ folder.
```
wget http://mftp.mmcheng.net/liuyun/rcf/data/HED-BSDS.tar.gz
```
Run the following command to start the testing:
```
python test.py --checkpoint bsds500_pascal_model.pth --save-dir /path/to/output/directory/
```
This pretrained model should achieve an ODS F-measure of 0.812.

For more information about RCF and edge quality evaluation, please refer to this page: yun-liu/RCF

Edge PR Curves

We have released the code and data for plotting the edge PR curves of many existing edge detectors here.

RCF based on other frameworks

PyTorch based RCF: yun-liu/RCF-PyTorch

Caffe based RCF: yun-liu/RCF

yun-liu / RCF-Jittor