Bregman Plug-and-Play Priors
Not on the map. Why?
Abstract (arXiv)
The past few years have seen a surge of activity around integration of deep learning networks and optimization algorithms for solving inverse problems. Recent work on plug-and-play priors (PnP), regularization by denoising (RED), and deep unfolding has shown the state-of-the-art performance of such integration in a variety of applications. However, the current paradigm for designing such algorithms is inherently Euclidean, due to the usage of the quadratic norm within the projection and proximal operators. We propose to broaden this perspective by considering a non-Euclidean setting based on the more general Bregman distance. Our new Bregman Proximal Gradient Method variant of PnP (PnP-BPGM) and Bregman Steepest Descent variant of RED (RED-BSD) replace the traditional updates in PnP and RED from the quadratic norms to more general Bregman distance. We present a theoretical convergence result for PnP-BPGM and demonstrate the effectiveness of our algorithms on Poisson linear inverse problems.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 4 Feb 2022.
Builds on
18 of 32 references.
References · 18
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
- 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
- 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
- 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
- 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
- 2019Plug-and-Play Methods Provably Converge with Properly Trained Denoiserscited by 197
- 2016Relatively-Smooth Convex Optimization by First-Order Methods, and Applicationscited by 108
- 2018Regularization by Denoising: Clarifications and New Interpretationscited by 102
- 2018Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholdscited by 83
- 2015Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolationcited by 78
6 more
- 2018An Online Plug-and-Play Algorithm for Regularized Image Reconstructioncited by 70
- 2019RARE: Image Reconstruction using Deep Priors Learned without Ground Truthcited by 64
- 2020Scalable Plug-and-Play ADMM with Convergence Guaranteescited by 49
- 2020Provable Convergence of Plug-and-Play Priors with MMSE denoiserscited by 39
- 2015Poisson Inverse Problems by the Plug-and-Play schemecited by 17
- 2020Boosting the Performance of Plug-and-Play Priors via Denoiser Scalingcited by 12
Built on by
Citing papers per year: 2023: 1; 2024: 1; 2025: 1.
3 papers.