An Archive of Reconstruction Algorithms for Snapshot Compressive Imaging

* Maintained by Zhihong Zhang

• BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging (The European Conference on Computer Vision 2020) by Ziheng Cheng, Ruiying Lu, Zhengjue Wang, Hao Zhang, Bo Chen, Ziyi Meng and Xin Yuan. [github]
• DeSCI : Rank Minimization for Snapshot Compressive Imaging (IEEE Transactions on Pattern Analysis and Machine Intelligence 2019) by Yang Liu*, Xin Yuan*, Jinli Suo, David J. Brady, and Qionghai Dai (Equal contributions). [pdf] [github] [arXiv] [doi] [data (Google Drive)] [data (Baidu Drive)]
• E2E-CNN: Deep Learning for Video Compressive Sensing in APL Photonics 5, 030801 (2020) by Mu Qiao*, Ziyi Meng*, Jiawei Ma, Xin Yuan (*Equal contributions). [pdf] [github]
• PnP-SCI: Plug-and-play Algorithms for Large-scale Snapshot Compressive Imaging in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020 (Oral) by Xin Yuan, Yang Liu, Jinli Suo, and Qionghai Dai. [pdf] [code_matlab] [code_python] [arXiv]
• RevSCI-net: Cheng, Ziheng, Bo Chen, Guanliang Liu, Hao Zhang, Ruiying Lu, Zhengjue Wang, and Xin Yuan. “Memory-Efficient Network for Large-Scale Video Compressive Sensing.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 16246–55, 2021. [pdf] [code]
• MetaSCI: Wang, Zhengjue, Hao Zhang, Ziheng Cheng, Bo Chen, and Xin Yuan. “MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2083–92, 2021. [pdf] [code]

• TSA-Net for CASSI: End-to-End Low Cost Compressive Spectral Imaging with Spatial-Spectral Self-Attention (ECCV (2020)) by Ziyi Meng*, Jiawei Ma*, Xin Yuan (*Equal contributions). [pdf] [github]

1. Please be aware that the codes containing in this repository is downloaded from the internet, and may not be updated to the latest version. For the latest version, please visit the original code website provided above for the updates.
2. Some codes may not contain source information as they are directly collected from 3rd party website.
3. Some algorithms are listed above without providing codes in this repository for their large memory size, but the code link is given above.