Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Mean Gradient Descent: An Empirical-Parameter-Free Approach for Inverse Problems in Imaging

Not Accessible

Your library or personal account may give you access

Abstract

We propose a new optimization approach, namely Mean Gradient Descent (MGD), to solve a variety of inverse problems in imaging science. The proposed algorithm does not involve empirical parameters, is noise robust and computationally inexpensive.

© 2021 The Author(s)

PDF Article
More Like This
Inverse design of a single wavelength filter based on the gradient descent algorithm

Lin He, Zhongzheng Lin, Yujie Chen, Yuanhui Wen, Yanfeng Zhang, and Siyuan Yu
M4A.268 Asia Communications and Photonics Conference (ACP) 2019

Solving Inverse Problems using Self-Supervised Deep Neural Nets

Jiapeng Liu, Muralidhar M. Balaji, Christopher A. Metzler, M. Salman Asif, and Prasanna Rangarajan
CTh5A.2 Computational Optical Sensing and Imaging (COSI) 2021

Empirical Bayesian Regularization of the Inverse Problem for Diffuse Optical Tomography with Multiple Priors

Farras Abdelnour and Theodore Huppert
BSuD28 Biomedical Optics (BIOMED) 2010

Poster Presentation

Media 1: PDF (686 KB)     
Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All Rights Reserved