Regularized Fourier Ptychography using an Online Plug-and-Play Algorithm
arXiv:1811.00120 · doi:10.1109/ICASSP.2019.8683057
Abstract
The plug-and-play priors (PnP) framework has been recently shown to achieve state-of-the-art results in regularized image reconstruction by leveraging a sophisticated denoiser within an iterative algorithm. In this paper, we propose a new online PnP algorithm for Fourier ptychographic microscopy (FPM) based on the fast iterative shrinkage/threshold algorithm (FISTA). Specifically, the proposed algorithm uses only a subset of measurements, which makes it scalable to a large set of measurements. We validate the algorithm by showing that it can lead to significant performance gains on both simulated and experimental data.
References in corpus (8)
- Wide-field, high-resolution Fourier ptychographic microscopy
- Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
- Fast Image Recovery Using Variable Splitting and Constrained Optimization
- BM3D Frames and Variational Image Deblurring
- Computational illumination for high-speed in vitro Fourier ptychographic microscopy
- Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolation
- Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
- An Online Plug-and-Play Algorithm for Regularized Image Reconstruction
Cited by in corpus (11)
- RARE: Image Reconstruction using Deep Priors Learned without Ground Truth
- Provable Convergence of Plug-and-Play Priors with MMSE denoisers
- SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priors
- Tensorial tomographic Fourier Ptychography with applications to muscle tissue imaging
- A New Recurrent Plug-and-Play Prior Based on the Multiple Self-Similarity Network
- CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems
- Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems
- Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priors
- TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
- Joint ptycho-tomography with deep generative priors
- Online Regularization by Denoising with Applications to Phase Retrieval