Compressed Sensing with Invertible Generative Models and Dependent Noise

We study image inverse problems with invertible generative priors, specifically normalizing flow models. Our formulation views the solution as the maximum a posteriori (MAP) estimate of the image given the measurements. Our general formulation allows for any differentiable noise model with long-range dependencies as well as non-linear differentiable forward operators. We establish theoretical recovery guarantees for denoising and compressed sensing under our framework. We also empirically validate our method on various inverse problems including compressed sensing with quantized measurements and denoising with highly structured noise patterns.

[1]  Eric Nalisnick,et al.  Normalizing Flows for Probabilistic Modeling and Inference , 2019, J. Mach. Learn. Res..

[2]  Yee Whye Teh,et al.  Detecting Out-of-Distribution Inputs to Deep Generative Models Using a Test for Typicality , 2019, ArXiv.

[3]  Ali Ahmed,et al.  Invertible generative models for inverse problems: mitigating representation error and dataset bias , 2019, ICML.

[4]  Timothy Lillicrap,et al.  Deep Compressed Sensing , 2019, ICML.

[5]  Jens Behrmann,et al.  Invertible Residual Networks , 2018, ICML.

[6]  Alexander A. Alemi,et al.  WAIC, but Why? Generative Ensembles for Robust Anomaly Detection , 2018 .

[7]  Yee Whye Teh,et al.  Do Deep Generative Models Know What They Don't Know? , 2018, ICLR.

[8]  David Duvenaud,et al.  FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models , 2018, ICLR.

[9]  Ullrich Köthe,et al.  Analyzing Inverse Problems with Invertible Neural Networks , 2018, ICLR.

[10]  Prafulla Dhariwal,et al.  Glow: Generative Flow with Invertible 1x1 Convolutions , 2018, NeurIPS.

[11]  Thomas G. Dietterich,et al.  Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations , 2018, 1807.01697.

[12]  Stefano Ermon,et al.  Modeling Sparse Deviations for Compressed Sensing using Generative Models , 2018, ICML.

[13]  Alexandros G. Dimakis,et al.  Compressed Sensing with Deep Image Prior and Learned Regularization , 2018, ArXiv.

[14]  Chinmay Hegde,et al.  Solving Linear Inverse Problems Using Gan Priors: An Algorithm with Provable Guarantees , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[15]  Andrea Vedaldi,et al.  Deep Image Prior , 2017, International Journal of Computer Vision.

[16]  Vladislav Voroninski,et al.  Global Guarantees for Enforcing Deep Generative Priors by Empirical Risk , 2017, IEEE Transactions on Information Theory.

[17]  Alexandros G. Dimakis,et al.  Compressed Sensing using Generative Models , 2017, ICML.

[18]  Max Welling,et al.  Improved Variational Inference with Inverse Autoregressive Flow , 2016, NIPS 2016.

[19]  Samy Bengio,et al.  Density estimation using Real NVP , 2016, ICLR.

[20]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[21]  Yoshua Bengio,et al.  NICE: Non-linear Independent Components Estimation , 2014, ICLR.

[22]  Xiaodong Li,et al.  Phase Retrieval via Wirtinger Flow: Theory and Algorithms , 2014, IEEE Transactions on Information Theory.

[23]  Aaron C. Courville,et al.  Generative adversarial networks , 2014, Commun. ACM.

[24]  R. Vershynin.  Estimation in High Dimensions: A Geometric Perspective , 2014, 1405.5103.

[25]  Yoshua Bengio,et al.  Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation , 2013, ArXiv.

[26]  E. Tabak,et al.  A Family of Nonparametric Density Estimation Algorithms , 2013 .

[27]  Yonina C. Eldar,et al.  Phase Retrieval via Matrix Completion , 2011, SIAM Rev..

[28]  Jie Tang,et al.  Prior image constrained compressed sensing (PICCS): a method to accurately reconstruct dynamic CT images from highly undersampled projection data sets. , 2008, Medical physics.

[29]  D. Donoho,et al.  Sparse MRI: The application of compressed sensing for rapid MR imaging , 2007, Magnetic resonance in medicine.

[30]  Karen O. Egiazarian,et al.  Image denoising with block-matching and 3D filtering , 2006, Electronic Imaging.

[31]  E. Candès,et al.  Stable signal recovery from incomplete and inaccurate measurements , 2005, math/0503066.

[32]  Michael I. Jordan,et al.  Decision-Making with Auto-Encoding Variational Bayes , 2020, NeurIPS.

[33]  Gitta Kutyniok.  Compressed Sensing , 2012 .

[34]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[35]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .