Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, EpiSciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Skip to Main content Skip to Navigation
Journal articles

Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior

Abstract : In this work we address the problem of solving ill-posed inverse problems in imaging where the prior is a variational autoencoder (VAE). 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 (JPMAP) 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. We also highlight the importance of correctly training the VAE using a denoising criterion, in order to ensure that the encoder generalizes well to out-of-distribution images, without affecting the quality of the generative model. This simple modification is key to providing robustness to the whole procedure. Finally we show how our joint MAP methodology relates to more common MAP approaches, and we propose a continuation scheme that makes use of our JPMAP algorithm to provide more robust MAP estimates. 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.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03151455
Contributor : Andrés Almansa Connect in order to contact the contributor
Submitted on : Tuesday, April 26, 2022 - 12:11:47 PM
Last modification on : Friday, April 29, 2022 - 3:35:40 AM

File

SIIMS_updated_2022-04-25.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03151455, version 4
  • ARXIV : 2103.01648

Relations

Citation

Mario González, Andrés Almansa, Pauline Tan. Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior. SIAM Journal on Imaging Sciences, Society for Industrial and Applied Mathematics, In press. ⟨hal-03151455v4⟩

Share

Metrics

Record views

124

Files downloads

48