Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior

11/14/2019
by   Mario González, et al.
0

In this paper we address the problem of solving ill-posed inverse problems in imaging where the prior is a neural generative model. Specifically we consider the decoupled case where the prior is trained once and can be reused for many different log-concave degradation models without retraining. Whereas previous MAP-based approaches to this problem lead to highly non-convex optimization algorithms, our approach computes the joint (space-latent) MAP that naturally leads to alternate optimization algorithms and to the use of a stochastic encoder to accelerate computations. The resulting technique is called JPMAP because it performs Joint Posterior Maximization using an Autoencoding Prior. We show theoretical and experimental evidence that the proposed objective function is quite close to bi-convex. Indeed it satisfies a weak bi-convexity property which is sufficient to guarantee that our optimization scheme converges to a stationary point. Experimental results also show the higher quality of the solutions obtained by our JPMAP approach with respect to other non-convex MAP approaches which more often get stuck in spurious local optima.

READ FULL TEXT

page 8

page 11

research
03/02/2021

Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior

In this work we address the problem of solving ill-posed inverse problem...
research
10/18/2020

Accelerated Algorithms for Convex and Non-Convex Optimization on Manifolds

We propose a general scheme for solving convex and non-convex optimizati...
research
02/21/2023

Learning Gradually Non-convex Image Priors Using Score Matching

In this paper, we propose a unified framework of denoising score-based m...
research
09/09/2020

Meta-learning for Multi-variable Non-convex Optimization Problems: Iterating Non-optimums Makes Optimum Possible

In this paper, we aim to address the problem of solving a non-convex opt...
research
03/27/2019

Decomposition of non-convex optimization via bi-level distributed ALADIN

Decentralized optimization algorithms are important in different context...
research
03/02/2018

Scalable Bayesian uncertainty quantification in imaging inverse problems via convex optimization

We propose a Bayesian uncertainty quantification method for large-scale ...
research
04/26/2016

Efficient Splitting-based Method for Global Image Smoothing

Edge-preserving smoothing (EPS) can be formulated as minimizing an objec...

Please sign up or login with your details

Forgot password? Click here to reset