# RefineContourNet

**Repository Path**: buptybx/RefineContourNet

## Basic Information

- **Project Name**: RefineContourNet
- **Description**: https://github.com/AndreKelm/RefineContourNet
- **Primary Language**: Unknown
- **License**: BSD-2-Clause
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-08-02
- **Last Updated**: 2024-05-30

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# RefineContourNet

RefineContourNet (RCN) is an Object Contour and Edge Detector. This is the test code and the best results of the paper Object Contour and Edge Detection with RefineContourNet; CAIP 2018

DOI: [10.1007/978-3-030-29888-3_20](https://arxiv.org/ct?url=https%3A%2F%2Fdx.doi.org%2F10.1007%2F978-3-030-29888-3_20&v=cf61f2c2)

## To test the RCN - please download refinenet-contour-master
* compile and setup the included MatConvNet-files (same procedure like for RefineNet [https://github.com/guosheng/refinenet]) 
* run the file demo_test_simple_voc_contour_tiff.m with MATLAB
* choose in this m-file the trained model for either Object Contour Detection or Edge Detection

## Best RCN-results:
* RCNVOC_NMS_results_on_BSDS500_val 
* RCNVOC_results_on_BSDS500_val 
* RCN_NMS_results_on_PASCAL_val 
* RCN_results_on_PASCAL_val