Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “plug-and-play priors”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

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

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.

Boosting↗

Provable Convergence of Plug-and-Play Priors With MMSE Denoisers

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. Here we address this gap by establishing the first theoretical convergence result for the iterative shrinkage/thresholding algorithm (ISTA) variant of PnP for MMSE denoisers. We show that the iterates produced by PnP-ISTA with an MMSE denoiser converge to a stationary point of some global cost function. We validate our analysis on sparse signal recovery in compressive sensing by comparing two types of denoisers, namely the exact MMSE denoiser and the approximate MMSE denoiser obtained by training a deep neural net.

97 MATHEMATICS AND COMPUTING↗

A Plug-and-Play Priors Approach for Solving Nonlinear Imaging Inverse Problems

In the past two decades, nonlinear image reconstruction methods have led to substantial improvements in the capabilities of numerous imaging systems. Such methods are traditionally formulated as optimization problems that are solved iteratively by simultaneously enforcing data consistency and incorporating prior models. Recently, the Plug-and-Play Priors (PPP) framework suggested that by using more sophisticated denoisers, not necessarily corresponding to an optimization objective, it is possible to improve the quality of reconstructed images. Here in this letter, we show that the PPP approach is applicable beyond linear inverse problems. In particular, we develop the fast iterative shrinkage/thresholding algorithm variant of PPP for model-based nonlinear inverse scattering. The key advantage of the proposed formulation over the original ADMM-based one is that it does not need to perform an inversion on the forward model. We show that the proposed method produces high quality images using both simulated and experimentally measured data.

97 MATHEMATICS AND COMPUTING↗

Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolation

Many material and biological samples in scientific imaging are characterized by nonlocal repeating structures. These are studied using scanning electron microscopy and electron tomography. Sparse sampling of individual pixels in a two-dimensional image acquisition geometry, or sparse sampling of projection images with large tilt increments in a tomography experiment, can enable high speed data acquisition and minimize sample damage caused by the electron beam. In this paper, we present an algorithm for electron tomographic reconstruction and sparse image interpolation that exploits the nonlocal redundancy in images. We adapt a framework, termed plug-and-play priors, to solve these imaging problems in a regularized inversion setting. The power of the plug-and-play approach is that it allows a wide array of modern denoising algorithms to be used as a “prior model” for tomography and image interpolation. We also present sufficient mathematical conditions that ensure convergence of the plug-and-play approach, and we use these insights to design a new nonlocal means denoising algorithm. Finally, we demonstrate that the algorithm produces higher quality reconstructions on both simulated and real electron microscope data, along with improved convergence properties compared to other methods.

47 OTHER INSTRUMENTATION↗

Scalable Plug-and-Play ADMM with Convergence Guarantees

Plug-and-play priors (PnP) is a broadly applicable methodology for solving inverse problems by exploiting statistical priors specified as denoisers. Recent work has reported the state-of-the-art performance of PnP algorithms using pre-trained deep neural nets as denoisers in a number of imaging applications. However, current PnP algorithms are impractical in large-scale settings due to their heavy computational and memory requirements. This work addresses this issue by proposing an incremental variant of the widely used PnP-ADMM algorithm, making it scalable to problems involving a large number measurements. Here, we theoretically analyze the convergence of the algorithm under a set of explicit assumptions, extending recent theoretical results in the area. Additionally, we show the effectiveness of our algorithm with nonsmooth data-fidelity terms and deep neural net priors, its fast convergence compared to existing PnP algorithms, and its scalability in terms of speed and memory.

97 MATHEMATICS AND COMPUTING↗

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

Plug-and-play priors (PnP) is a powerful framework for regularizing imaging inverse problems by using advanced denoisers within an iterative algorithm. Recent experimental evidence suggests that PnP algorithms achieve state-of-the-art performance in a range of imaging applications. Here, we introduce a new online PnP algorithm based on the proximal gradient method (PGM). The proposed algorithm uses only a subset of measurements at every iteration, which makes it scalable to very large datasets. We present a new theoretical convergence analysis, for both batch and online variants of PnP-PGM, for denoisers that do not necessarily correspond to proximal operators. We also present simulations illustrating the applicability of the algorithm to image reconstruction in diffraction tomography. Finally, the results in this paper have the potential to expand the applicability of the PnP framework to very large datasets.

97 MATHEMATICS AND COMPUTING↗

Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imaging: Theory, algorithms, and applications

Plug-and-play (PnP) priors constitute one of the most widely used frameworks for solving computational imaging problems through the integration of physical models and learned models. PnP leverages high-fidelity physical sensor models and powerful machine learning methods for prior modeling of data to provide state-of-the-art reconstruction algorithms. PnP algorithms alternate between minimizing a data fidelity term to promote data consistency and imposing a learned regularizer in the form of an image denoiser. Recent highly successful applications of PnP algorithms include biomicroscopy, computerized tomography (CT), magnetic resonance imaging (MRI), and joint ptychotomography. This article presents a unified and principled review of PnP by tracing its roots, describing its major variations, summarizing main results, and discussing applications in computational imaging. Additionally, we also point the way toward further developments by discussing recent results on equilibrium equations that formulate the problem associated with PnP algorithms.

97 MATHEMATICS AND COMPUTING↗

Joint ptycho-tomography with deep generative priors

Abstract Joint ptycho-tomography is a powerful computational imaging framework to recover the refractive properties of a 3D object while relaxing the requirements for probe overlap that is common in conventional phase retrieval. We use an augmented Lagrangian scheme for formulating the constrained optimization problem and employ an alternating direction method of multipliers (ADMM) for the joint solution. ADMM allows the problem to be split into smaller and computationally more efficient subproblems: ptychographic phase retrieval, tomographic reconstruction, and regularization of the solution. We extend our ADMM framework with plug-and-play (PnP) denoisers by replacing the regularization subproblem with a general denoising operator based on machine learning. While the PnP framework enables integrating such learned priors as denoising operators, tuning of the denoiser prior remains challenging. To overcome this challenge, we propose a denoiser parameter to control the effect of the denoiser and to accelerate the solution. In our simulations, we demonstrate that our proposed framework with parameter tuning and learned priors generates high-quality reconstructions under limited and noisy measurement data.

97 MATHEMATICS AND COMPUTING↗

Consensus Equilibrium for Subsurface Delineation

Heterogeneity and insufficient site characterization limit our knowledge of the subsurface. Inversion techniques, which minimize the mismatch between observations and model predictions, have become an essential tool of subsurface characterization. Most optimization-based approaches fail to incorporate various implicit priors and capture the geological complexity. We overcome these limitations by deploying the plug-and-play and consensus equilibrium (CE) strategies, which provide a flexible framework for image reconstruction. Our CE methodology for spatial delineation of geologic formations consists of an image denoiser and a variational auto-encoder (deep learning-based emulator). The former ameliorates the reconstruction noise, yielding well-defined geological structures; its mathematical equivalence with the proximal operator allows the deployment of advanced denoisers (e.g., CNN-based denoiser) that do not correspond to a regularization objective. The latter defines a geology prior that imposes a geological constraint, for example, continuity and shape of geological features, onto the reconstructed image. Here, we conduct a series of numerical experiments dealing with transient two-dimensional flow driven by a pumping well and natural hydraulic head gradient. They demonstrate the CE framework's ability to delineate, both probabilistically and deterministically, complex subsurface environments with sufficient quality.

42 ENGINEERING↗

Unrolled Video Super-Resolution Network with Autoregressive Prior for the Case of Known Motion

Real-time detection and classification of distant objects is necessary for many national security applications. However, when objects are far from the sensor, they occupy only a small number of pixels in the captured video, limiting the amount of visual detail available for recognition. State-of-the-art classification methods typically rely on high-resolution (HR) video streams to capture characteristic object features, but obtaining such detail is challenging for distant objects that occupy only a few pixels. This motivates the development of video super-resolution (VSR) methods that enhance object classification by recovering fine details from low-pixel representations. Current VSR methods rely either on model-based optimization, which is interpretable but computationally expensive, or on learning-based approaches, which are efficient and high-performing but often lack flexibility and interpretability. In this report, we propose an end-to-end trainable unrolled VSR network, UVSRNet, which super-resolves each frame in a video by exploiting sub-pixel motion between neighboring low-resolution (LR) frames as well as incorporating high-frequency detail from previously super-resolved frames. In particular, by unrolling a plug-and-play (PnP) half-quadratic splitting (HQS) algorithm, we leverage a model-based data-fitting module alongside a learning-based autoregressive prior module. This combination yields a method that maintains the flexibility and interpretability of model-based methods while achieving the performance advantages of learning-based methods.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Grid-Interactive Electric Vehicle and Building Coordination Using Coupled Distributed Control: Preprint

As an increasing number of controllable devices are introduced onto the grid, they can individually provide ancillary services in support of grid stability. However, the goals of each device differ due to their type and individual objectives, causing instances where they may conflict. To reduce the chances of these devices contributing to grid instability, these devices must effectively communicate in a cooperative manner to both meet their own needs while providing services to the grid. Previous work demonstrates that the NALD (Network Lasso-ADMM - Limited Communication - DMPC) algorithm allows coordination between two subsystems that use different control algorithms (building and charging stations) to provide services to the grid and individually optimize their performance in a specific scenario. The ideal NALD algorithm should be generalized to allow plug-and-play capabilities across devices of differing characteristics. This paper takes a step toward generalizability by updating the electric vehicle charging objective and re-defining the communication scheme compared to prior work to generalize the coordination and, as a result, improve the performance of the NALD algorithm.

ADVANCED PROPULSION SYSTEMS,ENERGY CONSERVATION, C↗

MiniCarb: a passive, occultation-viewing, 6U CubeSat for observations of CO 2 , CH 4 , and H 2 O

In this report we present the final design, environmental testing, and launch history of MiniCarb, a 6U CubeSat developed through a partnership between NASA Goddard Space Flight Center and Lawrence Livermore National Laboratory. MiniCarb’s science payload, developed at Goddard, was an occultation-viewing, passive laser heterodyne radiometer for observing methane, carbon dioxide, and water vapor in Earth’s atmosphere at ~1.6 µm s -1 . MiniCarb’s satellite, developed at Livermore, implemented their CubeSat Next Generation Bus plug-and-play architecture to produce a modular platform that could be tailored to a range of science payloads. Following the launch on 5 December 2019, MiniCarb traveled to the International Space Station and was set into orbit on 1 February 2020 via Northrop Grumman’s Cygnus capsule which deployed MiniCarb with tipoff rotation of about 20° s (significantly higher than the typical rate of 3° s -1 from prior CubeSats), from which the attitude control system was unable to recover resulting in a loss of power. In spite of this early failure, MiniCarb had many successes including rigorous environmental testing, successful deployment of its solar panels, and a successful test of the radio and communication through the Iridium network. This prior work and enticing cost (approximately $\$2$ M for the satellite and $\$$250 K for the payload) makes MiniCarb an ideal candidate for a low-cost and rapid rebuild as a single orbiter or constellation to globally observe key greenhouse gases.

47 OTHER INSTRUMENTATION↗

A Bayesian approach to real-time 3D tumor localization via monoscopic x-ray imaging during treatment delivery

Purpose: Monoscopic x-ray imaging with on-board kV devices is an attractive approach for real-time image guidance in modern radiation therapy such as VMAT or IMRT, but it falls short in providing reliable information along the direction of imaging x-ray. By effectively taking consideration of projection data at prior times and/or angles through a Bayesian formalism, the authors develop an algorithm for real-time and full 3D tumor localization with a single x-ray imager during treatment delivery. Methods: First, a prior probability density function is constructed using the 2D tumor locations on the projection images acquired during patient setup. Whenever an x-ray image is acquired during the treatment delivery, the corresponding 2D tumor location on the imager is used to update the likelihood function. The unresolved third dimension is obtained by maximizing the posterior probability distribution. The algorithm can also be used in a retrospective fashion when all the projection images during the treatment delivery are used for 3D localization purposes. The algorithm does not involve complex optimization of any model parameter and therefore can be used in a ''plug-and-play'' fashion. The authors validated the algorithm using (1) simulated 3D linear and elliptic motion and (2) 3D tumor motion trajectories of a lung and a pancreas patient reproduced by a physical phantom. Continuous kV images were acquired over a full gantry rotation with the Varian TrueBeam on-board imaging system. Three scenarios were considered: fluoroscopic setup, cone beam CT setup, and retrospective analysis. Results: For the simulation study, the RMS 3D localization error is 1.2 and 2.4 mm for the linear and elliptic motions, respectively. For the phantom experiments, the 3D localization error is < 1 mm on average and < 1.5 mm at 95th percentile in the lung and pancreas cases for all three scenarios. The difference in 3D localization error for different scenarios is small and is not statistically significant. Conclusions: The proposed algorithm eliminates the need for any population based model parameters in monoscopic image guided radiotherapy and allows accurate and real-time 3D tumor localization on current standard LINACs with a single x-ray imager.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Integrated Circuit Chip Improves Network Efficiency

Prior to 1999 and the development of SpaceWire, a standard for high-speed links for computer networks managed by the European Space Agency (ESA), there was no high-speed communications protocol for flight electronics. Onboard computers, processing units, and other electronics had to be designed for individual projects and then redesigned for subsequent projects, which increased development periods, costs, and risks. After adopting the SpaceWire protocol in 2000, NASA implemented the standard on the Swift mission, a gamma ray burst-alert telescope launched in November 2004. Scientists and developers on the James Webb Space Telescope further developed the network version of SpaceWire. In essence, SpaceWire enables more science missions at a lower cost, because it provides a standard interface between flight electronics components; new systems need not be custom built to accommodate individual missions, so electronics can be reused. New protocols are helping to standardize higher layers of computer communication. Goddard Space Flight Center improved on the ESA-developed SpaceWire by enabling standard protocols, which included defining quality of service and supporting plug-and-play capabilities. Goddard upgraded SpaceWire to make the routers more efficient and reliable, with features including redundant cables, simultaneous discrete broadcast pulses, prevention of network blockage, and improved verification. Redundant cables simplify management because the user does not need to worry about which connection is available, and simultaneous broadcast signals allow multiple users to broadcast low-latency side-band signal pulses across the network using the same resources for data communication. Additional features have been added to the SpaceWire switch to prevent network blockage so that more robust networks can be designed. Goddard s verification environment for the link-and-switch implementation continuously randomizes and tests different parts, constantly anticipating situations, which helps improve communications reliability. It has been tested in many different implementations for compatibility.

Source record↗

Hanford building 324 REC hot cell decommissioning approach - 15484

The 324 Building is a facility located at the Hanford Site and is undergoing decontamination and demolition (D and D) activities by Washington Closure Hanford (WCH). In October 1986, an in-cell leak of approximately 1.3 million curies occurred with a substantial fraction being lost into the subsurface soil beneath the floor of a large hot cell complex. Sampling under the hot cell floor revealed hot spots in the soil and cobble reading in excess of 10,000 R. In January of 2014, WCH contracted an AREVA lead team with Kurion as primary design agent to remove the B-Cell floor and highly contaminated underlying soils. The objective of this project is to remove the contaminated debris and soil and repackage them into the existing adjacent hot cells for final disposition as monoliths. The approach to this project uses an innovate combination of existing cell equipment, commercial equipment, and special tools to perform a series of completely remote operations. Also, a novel waste handling approach allows all the highly radioactive waste to remain within the existing cells. The remote handling approach to this project is to use customized off-the-shelf excavators which are mounted and operated remotely inside the cell. These can be moved and replaced remotely with a -Plug-and-Play- connection method. All the cables and utilities for the excavator and tools are managed through this cell connection with connections in a worker-accessible gallery space. The remote excavators are wall-mounted, which frees up the floor for the excavator work. The design also includes a transfer barrier which allows the B-Cell door to remain open during waste transfers while preventing spread of contamination between cells. The project balances the use of existing cell equipment such as cranes and shield doors, with the use of new remote equipment Existing equipment will be removed from the floor of the hot cell to adjacent cells. The concrete floor and stainless steel liner will then be remotely cut and removed, revealing the contaminated soil beneath the cell. The contaminated soil will be mixed with grout in the cell using the excavators and then placed in rigid bins. These bins will then be placed in the adjacent cells using existing overhead cranes. The waste containers allow optimal utilization of the limited adjacent hot cell space and improve the characteristics of the final waste monolith package. The system will use each bin once which significantly decreases the risk of contamination spread. The project includes a full-scale mockup facility in which all installation and operational activities will be tested and proven prior to hot cell construction activities. The mockup facility will also be used for operator training before actual hot work starts. This facility will remain available for use during operations with a full set of spares for redundancy and to support operations modeling during construction and remediation activities. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗