Deep Neural-network Prior for Orbit Recovery from Method of Moments

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Khoo, Yuehaw, Paul, Sounak, Sharon, Nir
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917577562783744
author Khoo, Yuehaw
Paul, Sounak
Sharon, Nir
author_facet Khoo, Yuehaw
Paul, Sounak
Sharon, Nir
contents Orbit recovery problems are a class of problems that often arise in practice and various forms. In these problems, we aim to estimate an unknown function after being distorted by a group action and observed via a known operator. Typically, the observations are contaminated with a non-trivial level of noise. Two particular orbit recovery problems of interest in this paper are multireference alignment and single-particle cryo-EM modelling. In order to suppress the noise, we suggest using the method of moments approach for both problems while introducing deep neural network priors. In particular, our neural networks should output the signals and the distribution of group elements, with moments being the input. In the multireference alignment case, we demonstrate the advantage of using the NN to accelerate the convergence for the reconstruction of signals from the moments. Finally, we use our method to reconstruct simulated and biological volumes in the cryo-EM setting.
format Preprint
id arxiv_https___arxiv_org_abs_2304_14604
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Deep Neural-network Prior for Orbit Recovery from Method of Moments
Khoo, Yuehaw
Paul, Sounak
Sharon, Nir
Methodology
Computer Vision and Pattern Recognition
Machine Learning
Numerical Analysis
Orbit recovery problems are a class of problems that often arise in practice and various forms. In these problems, we aim to estimate an unknown function after being distorted by a group action and observed via a known operator. Typically, the observations are contaminated with a non-trivial level of noise. Two particular orbit recovery problems of interest in this paper are multireference alignment and single-particle cryo-EM modelling. In order to suppress the noise, we suggest using the method of moments approach for both problems while introducing deep neural network priors. In particular, our neural networks should output the signals and the distribution of group elements, with moments being the input. In the multireference alignment case, we demonstrate the advantage of using the NN to accelerate the convergence for the reconstruction of signals from the moments. Finally, we use our method to reconstruct simulated and biological volumes in the cryo-EM setting.
title Deep Neural-network Prior for Orbit Recovery from Method of Moments
topic Methodology
Computer Vision and Pattern Recognition
Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2304.14604