Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221145321> ?p ?o ?g. }
- W4221145321 endingPage "769" @default.
- W4221145321 startingPage "759" @default.
- W4221145321 abstract "Image reconstruction from a sequence of a few linear measurements that are corrupted by signal-dependent normally distributed noise is an inverse problem with many biomedical imaging applications, such as computerized tomography and optical microscopy. In this study, we focus on single-pixel imaging, where the set-up acquires a down-sampled Hadamard transform of an image of the scene. Deep learning is a computationally efficient framework to solve inverse problems in imaging. Several neural-network architectures provide a link between deep and optimization-based image reconstruction methods. These deep-learning methods rely on a forward operator and lead to more interpretable networks. Here, we propose a novel network architecture obtained by unrolling an heuristic expectation-maximization algorithm. In particular, we compute the maximum <i>a posteriori</i> estimate of the unknown image given measurements corrupted by normally distributed signal-dependent noise. We show that the so-called expectation-maximization reconstruction network (EM-Net) applies to mixed Skellam-Gaussian noise models that are common in single-pixel imaging. We present reconstruction results from simulated and experimental single-pixel acquisitions. We show that EM-Net generalizes very well to noise levels not seen during training, despite having fewer learned parameters than alternative methods. The proposed EM-Net generally reconstructs images with fewer artifacts and higher signal-to-noise ratios, in particular in high-noise situations compared to other state of the art reconstruction algorithms that do not estimate the noise covariance." @default.
- W4221145321 created "2022-04-03" @default.
- W4221145321 creator A5038386064 @default.
- W4221145321 creator A5041616709 @default.
- W4221145321 creator A5075496055 @default.
- W4221145321 date "2022-01-01" @default.
- W4221145321 modified "2023-09-30" @default.
- W4221145321 title "Deep Expectation-Maximization for Single-Pixel Image Reconstruction With Signal-Dependent Noise" @default.
- W4221145321 cites W1512208174 @default.
- W4221145321 cites W1901129140 @default.
- W4221145321 cites W2021262032 @default.
- W4221145321 cites W2071005004 @default.
- W4221145321 cites W2079319869 @default.
- W4221145321 cites W2096669689 @default.
- W4221145321 cites W2108598243 @default.
- W4221145321 cites W2114456237 @default.
- W4221145321 cites W2122548617 @default.
- W4221145321 cites W2130392680 @default.
- W4221145321 cites W2136035751 @default.
- W4221145321 cites W2137534136 @default.
- W4221145321 cites W2142058898 @default.
- W4221145321 cites W2161623414 @default.
- W4221145321 cites W2181619750 @default.
- W4221145321 cites W2398810887 @default.
- W4221145321 cites W260788981 @default.
- W4221145321 cites W2623289458 @default.
- W4221145321 cites W2755327666 @default.
- W4221145321 cites W2788109278 @default.
- W4221145321 cites W2797400460 @default.
- W4221145321 cites W2803224943 @default.
- W4221145321 cites W2885076424 @default.
- W4221145321 cites W2889825089 @default.
- W4221145321 cites W2901589656 @default.
- W4221145321 cites W2943621407 @default.
- W4221145321 cites W2952020389 @default.
- W4221145321 cites W2963501224 @default.
- W4221145321 cites W2964231206 @default.
- W4221145321 cites W2971503239 @default.
- W4221145321 cites W2981551308 @default.
- W4221145321 cites W2994167575 @default.
- W4221145321 cites W3004829055 @default.
- W4221145321 cites W3026163403 @default.
- W4221145321 cites W3027535025 @default.
- W4221145321 cites W3047729951 @default.
- W4221145321 cites W3094430932 @default.
- W4221145321 cites W3094940122 @default.
- W4221145321 cites W3098900881 @default.
- W4221145321 cites W3100730608 @default.
- W4221145321 cites W3103372211 @default.
- W4221145321 cites W3103586216 @default.
- W4221145321 cites W3156407659 @default.
- W4221145321 cites W4230858297 @default.
- W4221145321 cites W4375802365 @default.
- W4221145321 doi "https://doi.org/10.1109/tci.2022.3200841" @default.
- W4221145321 hasPublicationYear "2022" @default.
- W4221145321 type Work @default.
- W4221145321 citedByCount "1" @default.
- W4221145321 countsByYear W42211453212023 @default.
- W4221145321 crossrefType "journal-article" @default.
- W4221145321 hasAuthorship W4221145321A5038386064 @default.
- W4221145321 hasAuthorship W4221145321A5041616709 @default.
- W4221145321 hasAuthorship W4221145321A5075496055 @default.
- W4221145321 hasBestOaLocation W42211453213 @default.
- W4221145321 hasConcept C106430172 @default.
- W4221145321 hasConcept C11413529 @default.
- W4221145321 hasConcept C115961682 @default.
- W4221145321 hasConcept C141379421 @default.
- W4221145321 hasConcept C153180895 @default.
- W4221145321 hasConcept C154945302 @default.
- W4221145321 hasConcept C160633673 @default.
- W4221145321 hasConcept C173801870 @default.
- W4221145321 hasConcept C31972630 @default.
- W4221145321 hasConcept C41008148 @default.
- W4221145321 hasConcept C4199805 @default.
- W4221145321 hasConcept C9417928 @default.
- W4221145321 hasConcept C99498987 @default.
- W4221145321 hasConceptScore W4221145321C106430172 @default.
- W4221145321 hasConceptScore W4221145321C11413529 @default.
- W4221145321 hasConceptScore W4221145321C115961682 @default.
- W4221145321 hasConceptScore W4221145321C141379421 @default.
- W4221145321 hasConceptScore W4221145321C153180895 @default.
- W4221145321 hasConceptScore W4221145321C154945302 @default.
- W4221145321 hasConceptScore W4221145321C160633673 @default.
- W4221145321 hasConceptScore W4221145321C173801870 @default.
- W4221145321 hasConceptScore W4221145321C31972630 @default.
- W4221145321 hasConceptScore W4221145321C41008148 @default.
- W4221145321 hasConceptScore W4221145321C4199805 @default.
- W4221145321 hasConceptScore W4221145321C9417928 @default.
- W4221145321 hasConceptScore W4221145321C99498987 @default.
- W4221145321 hasFunder F4320320883 @default.
- W4221145321 hasFunder F4320326804 @default.
- W4221145321 hasLocation W42211453211 @default.
- W4221145321 hasLocation W42211453212 @default.
- W4221145321 hasLocation W42211453213 @default.
- W4221145321 hasLocation W42211453214 @default.
- W4221145321 hasLocation W42211453215 @default.
- W4221145321 hasLocation W42211453216 @default.
- W4221145321 hasLocation W42211453217 @default.