• Corpus ID: 238583106

Revisit Dictionary Learning for Video Compressive Sensing under the Plug-and-Play Framework

  title={Revisit Dictionary Learning for Video Compressive Sensing under the Plug-and-Play Framework},
  author={Qing Yang and Yaping Zhao},
Aiming at high-dimensional (HD) data acquisition and analysis, snapshot compressive imaging (SCI) obtains the 2D compressed measurement of HD data with optical imaging systems and reconstructs HD data using compressive sensing algorithms. While the Plug-and-Play (PnP) framework offers an emerging solution to SCI reconstruction, its intrinsic denoising process is still a challenging problem. Unfortunately, existing denoisers in the PnP framework either suffer limited performance or require… 

Figures and Tables from this paper


Deep learning for video compressive sensing
This paper builds both an end-to-end convolutional neural network (E2E-CNN) and a Plug-and-Play (PnP) framework with deep denoising priors and compares them with the iterative baseline algorithm GAP-TV and the state-of-the-art DeSCI on real data.
Plug-and-Play Algorithms for Video Snapshot Compressive Imaging
A joint reconstruction and demosaicing paradigm is developed for flexible and high quality reconstruction of color video SCI systems and extensive results on both simulation and real datasets verify the superiority of the proposed PnP algorithm.
Rank Minimization for Snapshot Compressive Imaging
A joint model is built to integrate the nonlocal self-similarity of video/hyperspectral frames and the rank minimization approach with the SCI sensing process and an alternating minimization algorithm is developed to solve the non-convex problem of SCI reconstruction.
Deep Tensor ADMM-Net for Snapshot Compressive Imaging
A deep tensor ADMM-Net for video SCI systems that provides high-quality decoding in seconds with comparable visual results with the state-of-the-art methods but in much shorter running time is proposed.
Snapshot Compressive Imaging: Theory, Algorithms, and Applications
Recent advances in SCI hardware, theory, and algorithms are reviewed, including both optimizationbased and deep learning-based algorithms.
GAP-net for Snapshot Compressive Imaging
This paper proposes an SCI recovery algorithm, namely GAP-net, which unfolds the generalized alternating projection (GAP) algorithm, and shows that G AP-net is flexible with respect to signal modulation implying that a trained Gap-net decoder can be applied in different systems.
BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging
This work considers the problem of video snapshot compressive imaging (SCI), where multiple high-speed frames are coded by different masks and then summed to a single measurement, and proposes a recurrent networks solution, for the first time that recurrent networks are employed to SCI problem.
Snapshot Compressed Sensing: Performance Bounds and Algorithms
  • S. Jalali, Xin Yuan
  • Computer Science, Mathematics
    IEEE Transactions on Information Theory
  • 2019
It is shown that, in the cases of both noise-free and noisy measurements, combining the proposed algorithms with a customized video compression code, designed to exploit nonlocal structures of video frames, significantly improves the state-of-the-art performance.
FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising
The proposed FFDNet works on downsampled sub-images, achieving a good trade-off between inference speed and denoising performance, and enjoys several desirable properties, including the ability to handle a wide range of noise levels effectively with a single network.
Plug-and-Play priors for model based reconstruction
This paper demonstrates with some simple examples how Plug-and-Play priors can be used to mix and match a wide variety of existing denoising models with a tomographic forward model, thus greatly expanding the range of possible problem solutions.