Provable Convergence of Plug-and-Play Priors with MMSE denoisers

@article{Xu2020ProvableCO,
  title={Provable Convergence of Plug-and-Play Priors with MMSE denoisers},
  author={Xiaojian Xu and Yu Sun and Jia-Ming Liu and Brendt Wohlberg and Ulugbek S. Kamilov},
  journal={arXiv: Signal Processing},
  year={2020}
}
  • Xiaojian Xu, Yu Sun, +2 authors Ulugbek S. Kamilov
  • Published 2020
  • Mathematics, Engineering
  • arXiv: Signal Processing
  • Plug-and-play priors (PnP) is a methodology for regularized image reconstruction that specifies the prior through an image denoiser. While PnP algorithms are well understood for denoisers performing maximum a posteriori probability (MAP) estimation, they have not been analyzed for the minimum mean squared error (MMSE) denoisers. This letter addresses this gap by establishing the first theoretical convergence result for the iterative shrinkage/thresholding algorithm (ISTA) variant of PnP for… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 47 REFERENCES

    An Online Plug-and-Play Algorithm for Regularized Image Reconstruction

    Scene-Adapted plug-and-play algorithm with convergence guarantees

    Performance Analysis of Plug-and-Play ADMM: A Graph Signal Processing Perspective

    • Stanley H. Chan
    • Computer Science, Mathematics
    • IEEE Transactions on Computational Imaging
    • 2019

    Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

    VIEW 3 EXCERPTS