Boosting the Performance of Plug-and-Play Priors via Denoiser Scaling

Conference · Sun Nov 01 04:00:00 EST 2020

DOI:https://doi.org/10.1109/ieeeconf51394.2020.9443410· OSTI ID:1823749

Xu, Xiaojian ^[1]; Liu, Jiaming ^[1]; Sun, Yu ^[1]; Wohlberg, Brendt ^[2]; Kamilov, Ulugbek S. ^[1]

---

1. Washington Univ., St. Louis, MO (United States)
2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Plug-and-play priors (PnP) is an image reconstruction framework that utilizes an image denoiser as an imaging prior. Unlike traditional regularized inversion, PnP does not require the prior to be expressible in the form of a regularization function. This flexibility enables PnP algorithms to exploit the most effective image denoisers, leading to their state-of-the-art performance in various imaging tasks. However, many powerful denoisers, such as the ones based on convolutional neural networks (CNNs), do not have tunable parameters that would allow controlling their influence within PnP. To address this issue, in this paper, we introduce a scaling parameter that adjusts the magnitude of the denoiser input and output. We theoretical justify the denoiser scaling from the perspectives of proximal optimization, statistical estimation, and consensus equilibrium. Finally, we provide numerical experiments demonstrating the ability of denoiser scaling to systematically improve the performance of PnP for denoising CNN priors that do not have explicitly tunable parameters.

• Research Organization: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
• Sponsoring Organization: USDOE Laboratory Directed Research and Development (LDRD) Program
• DOE Contract Number: 89233218CNA000001
• OSTI ID: 1823749
• Report Number(s): LA-UR--19-32413
• Country of Publication: United States
• Language: English

Related Subjects

Boosting
CNN priors
Computers
Convolutional neural networks
Estimation
Imaging
Information Science
Inverse problems
Mathematics
Noise reduction
PnP algorithms
Regularized image reconstruction
consensus equilibrium
convolutional neural nets
convolutional neural networks
deep learning
denoiser scaling
image denoiser
image denoising
image reconstruction
plug and play priors
plug-and-play priors
proximal optimization
regularization function
regularization parameter
statistical estimation