Home

Awesome

SAM

We proposed a stereo attention module (SAM) to extend arbitrary single image SR methods for stereo image SR. [<a href="https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8998204">PDF</a>] <br>

We release the demo of SRResNet+SAM in a new branch. [<a href="https://github.com/XinyiYing/SAM/tree/SRResNet_SAM">Code</a>] <br><br>

Architecture of SAM

<img src="https://raw.github.com/XinyiYing/SAM/master/Figs/Network.jpg" width="600"><br>

Visualization of Generated Attention Maps

<img src="https://raw.github.com/XinyiYing/SAM/master/Figs/AttMap.jpg" width="600"><br>

Quantitative Results

<img src="https://raw.github.com/XinyiYing/SAM/master/Figs/Quantitative.jpg" width="1000"><br>

Qualitative Results

<img src="https://raw.github.com/XinyiYing/SAM/master/Figs/Qualitative.jpg" width="1000"><br>

Citiation

If you find our work helpful, please cite: <br><br>

@article{SAM,
  title={A Stereo Attention Module for Stereo Image Super-Resolution},
  author={Ying, Xinyi and Wang, Yingqian and Wang, Longguang and Sheng, Weidong and An, Wei and Guo, Yulan},
  journal={IEEE Signal Processing Letters},
  year={2020},
  volume={27},
  pages={496-500},
  publisher={IEEE}
}

Related Work

Contact

You can contact us at yingxinyi18@nudt.edu.cn or wangyingqian16@nudt.edu.cn for any question about this work. <br>