Learning-Based Image Reconstruction via Parallel Proximal Algorithm

In the past decade, sparsity-driven regularization has led to the advancement of image reconstruction algorithms. Traditionally, such regularizers rely on analytical models of sparsity [e.g., total variation (TV)]. However, more recent methods are increasingly centered around data-driven arguments i...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE signal processing letters Ročník 25; číslo 7; s. 989 - 993
Hlavní autoři: Bostan, Emrah, Kamilov, Ulugbek S., Waller, Laura
Médium: Journal Article
Jazyk:angličtina
Vydáno: IEEE 01.07.2018
Témata:
Analytical models
Computational modeling
Image reconstruction
inverse problems
iterative shrinkage
learning
Signal processing algorithms
statistical modeling
Training
Transforms
ISSN:1070-9908, 1558-2361
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In the past decade, sparsity-driven regularization has led to the advancement of image reconstruction algorithms. Traditionally, such regularizers rely on analytical models of sparsity [e.g., total variation (TV)]. However, more recent methods are increasingly centered around data-driven arguments inspired by deep learning. In this letter, we propose to generalize TV regularization by replacing the 11 -penalty with an alternative prior that is trainable. Specifically, our method learns the prior via extending the recently proposed fast parallel proximal algorithm to incorporate data-adaptive proximal operators. The proposed framework does not require additional inner iterations for evaluating the proximal mappings of the corresponding learned prior. Moreover, our formalism ensures that the training and reconstruction processes share the same algorithmic structure, making the endto-end implementation intuitive. As an example, we demonstrate our algorithm on the problem of deconvolution in a fluorescence microscope.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2018.2833812