Deep Neural-network Prior for Orbit Recovery from Method of Moments
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| 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 |