Home

Awesome

GFRNet

Official code repository for paper Guided Focal Stack Refinement Network for Light Field Salient Object Detection (ICME2023). Coming soon!

Overall Architecture

<p align="center"> <img src="picture/network.png" width="100%"/> <br /> <em> Overall architecture of the proposed GFRNet. </em> </p>

Inference

Download the pretrained model at Baidu Driver (PSW: xmhu).

Generate saliency maps:

Results

<p align="center"> <img src="picture/result.PNG" width="100%"/> <br /> <em> Quantitative Results. The best result is highlighted in bold. “N/T” denotes unavailable results. ↑/↓ means that a larger/smaller value is better. </em> </p>

Download

The saliency maps can be download from Baidu Driver (PSW: 1iuf).

Citation

Please cite the following paper if you use this repository in your research:

@inproceedings{yuan2023guided,
  title={Guided focal stack refinement network for light field salient object detection},
  author={Yuan, Bo and Jiang, Yao and Fu, Keren and Zhao, Qijun},
  booktitle={2023 IEEE International Conference on Multimedia and Expo (ICME)},
  pages={2387--2392},
  year={2023},
  organization={IEEE}
}

Any questions regarding this work can contact yuanboera@qq.com.