Deep expectation-maximization for single-pixel image reconstruction with signal-dependent noise
Résumé
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, positron emission tomography, and optical microscopy. In this study, we focus on single-pixel imaging, where the setup acquires a down-sampled Hadamard transform of an image of the scene. Deep learning is a very 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 the expectation-maximization algorithm. In particular, we compute the maximum a-posteriori 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 the unseen noise levels 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.
Fichier principal
Deep_Expectation_Maximization_for_image_reconstruction_from_Under_Sampled_Data_with_signal_dependent_normally_distributed_noise.pdf (855.01 Ko)
Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)