Learned reconstruction methods with convergence guarantees: A survey of concepts and applications
In recent years, deep learning has achieved remarkable empirical success for image
reconstruction. This has catalyzed an ongoing quest for the precise characterization of the …
reconstruction. This has catalyzed an ongoing quest for the precise characterization of the …
Physics-inspired compressive sensing: Beyond deep unrolling
As an emerging paradigm for signal acquisition and reconstruction, compressive sensing
(CS) achieves high-speed sampling and compression jointly and has found its way into …
(CS) achieves high-speed sampling and compression jointly and has found its way into …
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 …
computational imaging problems through the integration of physical models and learned …
Uncertainty-driven loss for single image super-resolution
In low-level vision such as single image super-resolution (SISR), traditional MSE or L1 loss
function treats every pixel equally with the assumption that the importance of all pixels is the …
function treats every pixel equally with the assumption that the importance of all pixels is the …
Jfb: Jacobian-free backpropagation for implicit networks
A promising trend in deep learning replaces traditional feedforward networks with implicit
networks. Unlike traditional networks, implicit networks solve a fixed point equation to …
networks. Unlike traditional networks, implicit networks solve a fixed point equation to …
Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging: Combining physics and machine learning for improved medical imaging
Physics-driven deep learning methods have emerged as a powerful tool for computational
magnetic resonance imaging (MRI) problems, pushing reconstruction performance to new …
magnetic resonance imaging (MRI) problems, pushing reconstruction performance to new …
DEQ-MPI: A deep equilibrium reconstruction with learned consistency for magnetic particle imaging
Magnetic particle imaging (MPI) offers unparalleled contrast and resolution for tracing
magnetic nanoparticles. A common imaging procedure calibrates a system matrix (SM) that …
magnetic nanoparticles. A common imaging procedure calibrates a system matrix (SM) that …
Near-exact recovery for tomographic inverse problems via deep learning
This work is concerned with the following fundamental question in scientific machine
learning: Can deep-learning-based methods solve noise-free inverse problems to near …
learning: Can deep-learning-based methods solve noise-free inverse problems to near …
Online deep equilibrium learning for regularization by denoising
Abstract Plug-and-Play Priors (PnP) and Regularization by Denoising (RED) are widely-
used frameworks for solving imaging inverse problems by computing fixed-points of …
used frameworks for solving imaging inverse problems by computing fixed-points of …
Iterative residual optimization network for limited-angle tomographic reconstruction
Limited-angle tomographic reconstruction is one of the typical ill-posed inverse problems,
leading to edge divergence with degraded image quality. Recently, deep learning has been …
leading to edge divergence with degraded image quality. Recently, deep learning has been …