Motivating bilevel approaches to filter learning: A case study
C Crockett, JA Fessler - 2021 IEEE International Conference on …, 2021 - ieeexplore.ieee.org
The recent trend in regularization methods for inverse problems is to replace handcrafted
sparsifying operators with data-driven approaches. Although using such machine learning …
sparsifying operators with data-driven approaches. Although using such machine learning …
Incorporating handcrafted filters in convolutional analysis operator learning for ill-posed inverse problems
C Crockett, D Hong, IY Chun… - 2019 IEEE 8th …, 2019 - ieeexplore.ieee.org
Convolutional analysis operator learning (CAOL) enables the unsupervised training of
convolutional sparsifying autoencoders, taking advantage of large datasets to obtain high …
convolutional sparsifying autoencoders, taking advantage of large datasets to obtain high …
[PDF][PDF] A neural-network-based convex regularizer for image reconstruction
The emergence of deep-learning-based methods for solving inverse problems has enabled
a significant increase in reconstruction quality. Unfortunately, these new methods often lack …
a significant increase in reconstruction quality. Unfortunately, these new methods often lack …
A neural-network-based convex regularizer for inverse problems
The emergence of deep-learning-based methods to solve image-reconstruction problems
has enabled a significant increase in quality. Unfortunately, these new methods often lack …
has enabled a significant increase in quality. Unfortunately, these new methods often lack …
Iteratively Refined Image Reconstruction with Learned Attentive Regularizers
We propose a regularization scheme for image reconstruction that leverages the power of
deep learning while hinging on classic sparsity-promoting models. Many deep-learning …
deep learning while hinging on classic sparsity-promoting models. Many deep-learning …
Plug-and-play regularization using linear solvers
P Nair, KN Chaudhury - IEEE Transactions on Image …, 2022 - ieeexplore.ieee.org
There has been tremendous research on the design of image regularizers over the years,
from simple Tikhonov and Laplacian to sophisticated sparsity and CNN-based regularizers …
from simple Tikhonov and Laplacian to sophisticated sparsity and CNN-based regularizers …
A projectional ansatz to reconstruction
S Dittmer, P Maass - arXiv preprint arXiv:1907.04675, 2019 - arxiv.org
Recently the field of inverse problems has seen a growing usage of mathematically only
partially understood learned and non-learned priors. Based on first principles, we develop a …
partially understood learned and non-learned priors. Based on first principles, we develop a …
Compressive learning of deep regularization for denoising
H Shi, Y Traonmilin, JF Aujol - … Conference on Scale Space and Variational …, 2023 - Springer
Solving ill-posed inverse problems can be done accurately if a regularizer well adapted to
the nature of the data is available. Such regularizer can be systematically linked with the …
the nature of the data is available. Such regularizer can be systematically linked with the …
Learning pseudo-contractive denoisers for inverse problems
Deep denoisers have shown excellent performance in solving inverse problems in signal
and image processing. In order to guarantee the convergence, the denoiser needs to satisfy …
and image processing. In order to guarantee the convergence, the denoiser needs to satisfy …
Sparse anett for solving inverse problems with deep learning
We propose a sparse reconstruction framework (aNETT) for solving inverse problems.
Opposed to existing sparse reconstruction techniques that are based on linear sparsifying …
Opposed to existing sparse reconstruction techniques that are based on linear sparsifying …