Fast Compressive Sensing Recovery Using Generative Models with Structured Latent Variables
Authors:
- 1 May 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2967-2971
Abstract
Deep learning models have significantly improved the visual quality and accuracy on compressive sensing recovery. In this paper, we propose an algorithm for signal reconstruction from compressed measurements with image priors captured by a generative model. We search and constrain on latent variable space to make the method stable when the number of compressed measurements is extremely limited. We show that, by exploiting certain structures of the latent variables, the proposed method produces improved reconstruction accuracy and preserves realistic and non-smooth features in the image. Our algorithm achieves high computation speed by projecting between the original signal space and the latent variable space in an alternating fashion.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Deep Learning Face Attributes in the Wild2015
- BM3D-AMP: A new image recovery algorithm based on BM3D denoising2015
- Proximal AlgorithmsFoundations and Trends® in Optimization, 2014
- Image denoising: Can plain neural networks compete with BM3D?2012
- Compressive Sensing on Manifolds Using a Nonparametric Mixture of Factor Analyzers: Algorithm and Performance BoundsIEEE Transactions on Signal Processing, 2010
- Message-passing algorithms for compressed sensingProceedings of the National Academy of Sciences, 2009
- A Simple Proof of the Restricted Isometry Property for Random MatricesConstructive Approximation, 2008
- Random Projections of Smooth ManifoldsFoundations of Computational Mathematics, 2007
- Compressed sensingIEEE Transactions on Information Theory, 2006
- Least angle regressionThe Annals of Statistics, 2004