Deep image prior and weighted anisotropic-isotropic total variation regularization for solving linear inverse problems

Yujia Xie, Wengu Chen, Huanmin Ge and Michael K. Ng

Applied Mathematics and Computation, 2024, vol. 482, issue C

Abstract: Deep learning, particularly unsupervised techniques, has been widely used to solve linear inverse problems due to its flexibility. A notable unsupervised approach is the deep image prior (DIP), which employs a predetermined deep neural network to regularize inverse problems by imposing constraints on the generated image. This article introduces an optimization technique (DIP-AITV) by combining the DIP with the weighted anisotropic-isotropic total variation (AITV) regularization. Furthermore, we utilize the alternating direction method of multipliers (ADMM), a highly flexible optimization technique, to solve the DIP-AITV minimization problem effectively. To demonstrate the benefits of the proposed DIP-AITV method over the state-of-the-art DIP, DIP-TV, DIP-WTV and CS-DIP, we solve two linear inverse problems, i.e., image denoising and compressed sensing. Computation examples on the MSE and PSNR values show that our method outperforms the existing DIP-based methods in both synthetic and real grayscale and color images.

Keywords: Deep image prior; The anisotropic-isotropic total variation; Compressed sensing; Image denoising (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0096300324004132
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:apmaco:v:482:y:2024:i:c:s0096300324004132

DOI: 10.1016/j.amc.2024.128952

Access Statistics for this article

Applied Mathematics and Computation is currently edited by Theodore Simos

More articles in Applied Mathematics and Computation from Elsevier
Bibliographic data for series maintained by Catherine Liu ().