Compressed Sensing using Generative Models
نویسندگان
چکیده
The goal of compressed sensing is to estimate a vector from an underdetermined system of noisy linear measurements, by making use of prior knowledge on the structure of vectors in the relevant domain. For almost all results in this literature, the structure is represented by sparsity in a well-chosen basis. We show how to achieve guarantees similar to standard compressed sensing but without employing sparsity at all. Instead, we suppose that vectors lie near the range of a generative model G : R ! R. Our main theorem is that, if G is L-Lipschitz, then roughly O(k logL) random Gaussian measurements suffice for an `
منابع مشابه
Task-Aware Compressed Sensing with Generative Adversarial Networks
In recent years, neural network approaches have been widely adopted for machine learning tasks, with applications in computer vision. More recently, unsupervised generative models based on neural networks have been successfully applied to model data distributions via low-dimensional latent spaces. In this paper, we use Generative Adversarial Networks (GANs) to impose structure in compressed sen...
متن کاملSUNLayer: Stable denoising with generative networks
It has been experimentally established that deep neural networks can be used to produce good generative models for real world data. It has also been established that such generative models can be exploited to solve classical inverse problems like compressed sensing and super resolution. In this work we focus on the classical signal processing problem of image denoising. We propose a theoretical...
متن کاملAccelerating Magnetic Resonance Imaging through Compressed Sensing Theory in the Direction space-k
Magnetic Resonance Imaging (MRI) is a noninvasive imaging method widely used in medical diagnosis. Data in MRI are obtained line-by-line within the K-space, where there are usually a great number of such lines. For this reason, magnetic resonance imaging is slow. MRI can be accelerated through several methods such as parallel imaging and compressed sensing, where a fraction of the K-space lines...
متن کاملFrames for compressed sensing using coherence
We give some new results on sparse signal recovery in the presence of noise, for weighted spaces. Traditionally, were used dictionaries that have the norm equal to 1, but, for random dictionaries this condition is rarely satised. Moreover, we give better estimations then the ones given recently by Cai, Wang and Xu.
متن کاملCompressive Sensing via Convolutional Factor Analysis
We solve the compressive sensing problem via convolutional factor analysis, where the convolutional dictionaries are learned in situ from the compressed measurements. An alternating direction method of multipliers (ADMM) paradigm for compressive sensing inversion based on convolutional factor analysis is developed. The proposed algorithm provides reconstructed images as well as features, which ...
متن کامل