Bagged Deep Image Prior for Recovering Images in the Presence of Speckle Noise
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909119776030720 |
|---|---|
| author | Chen, Xi Hou, Zhewen Metzler, Christopher A. Maleki, Arian Jalali, Shirin |
| author_facet | Chen, Xi Hou, Zhewen Metzler, Christopher A. Maleki, Arian Jalali, Shirin |
| contents | We investigate both the theoretical and algorithmic aspects of likelihood-based methods for recovering a complex-valued signal from multiple sets of measurements, referred to as looks, affected by speckle (multiplicative) noise. Our theoretical contributions include establishing the first existing theoretical upper bound on the Mean Squared Error (MSE) of the maximum likelihood estimator under the deep image prior hypothesis. Our theoretical results capture the dependence of MSE upon the number of parameters in the deep image prior, the number of looks, the signal dimension, and the number of measurements per look. On the algorithmic side, we introduce the concept of bagged Deep Image Priors (Bagged-DIP) and integrate them with projected gradient descent. Furthermore, we show how employing Newton-Schulz algorithm for calculating matrix inverses within the iterations of PGD reduces the computational complexity of the algorithm. We will show that this method achieves the state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15635 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Bagged Deep Image Prior for Recovering Images in the Presence of Speckle Noise Chen, Xi Hou, Zhewen Metzler, Christopher A. Maleki, Arian Jalali, Shirin Information Theory Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Applications We investigate both the theoretical and algorithmic aspects of likelihood-based methods for recovering a complex-valued signal from multiple sets of measurements, referred to as looks, affected by speckle (multiplicative) noise. Our theoretical contributions include establishing the first existing theoretical upper bound on the Mean Squared Error (MSE) of the maximum likelihood estimator under the deep image prior hypothesis. Our theoretical results capture the dependence of MSE upon the number of parameters in the deep image prior, the number of looks, the signal dimension, and the number of measurements per look. On the algorithmic side, we introduce the concept of bagged Deep Image Priors (Bagged-DIP) and integrate them with projected gradient descent. Furthermore, we show how employing Newton-Schulz algorithm for calculating matrix inverses within the iterations of PGD reduces the computational complexity of the algorithm. We will show that this method achieves the state-of-the-art performance. |
| title | Bagged Deep Image Prior for Recovering Images in the Presence of Speckle Noise |
| topic | Information Theory Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Applications |
| url | https://arxiv.org/abs/2402.15635 |