paper-with-me

홈 › Papers

Inverse problem regularization with hierarchical variational autoencoders

2023-03-20 · ICCV 2023 1 · Jean Prost, Antoine Houdard, Andrés Almansa, Nicolas Papadakis

In this paper, we propose to regularize ill-posed inverse problems using a deep hierarchical variational autoencoder (HVAE) as an image prior. The proposed method synthesizes the advantages of i) denoiser-based Plug \& Play approaches and ii) generative model based approaches to inverse problems. First, we exploit VAE properties to design an efficient algorithm that benefits from convergence guarantees of Plug-and-Play (PnP) methods. Second, our approach is not restricted to specialized datasets and the proposed PnP-HVAE model is able to solve image restoration problems on natural images of any size. Our experiments show that the proposed PnP-HVAE method is competitive with both SOTA denoiser-based PnP approaches, and other SOTA restoration methods based on generative models.

📄 PDF Abstract BibTeX arXiv:2303.11217

Code (1)

jprost76/pnp-hvae 공식 구현 pytorch

Tasks

Image Restoration

Methods 이 논문이 사용한 방법론

PnP PnP, or Poll and Pool, is sampling module extension for DETR-type architectures that adaptively allocates its computation…

Similar Papers 제목 키워드 기반

Enhanced uncertainty quantification variational autoencoders for the solution of Bayesian inverse problems

2025-02-18 · Andrea Tonini, Luca Dede'

Among other uses, neural networks are a powerful tool for solving deterministic and Bayesian inverse problems in real-time. In the Bayesian framework, variational autoencoders, a specialized type of neural network, enabl…

Uncertainty Quantification

Variational Bayes image restoration with compressive autoencoders

2023-11-29 · Maud Biquard, Marie Chabert, Florence Genin, Christophe Latry 외

Regularization of inverse problems is of paramount importance in computational imaging. The ability of neural networks to learn efficient image representations has been recently exploited to design powerful data-driven r…

Image RestorationVariational Inference

A Variational Inference Approach to Inverse Problems with Gamma Hyperpriors

2021-11-26 · Shiv Agrawal, Hwanwoo Kim, Daniel Sanz-Alonso, Alexander Strang

Hierarchical models with gamma hyperpriors provide a flexible, sparse-promoting framework to bridge $L^1$ and $L^2$ regularizations in Bayesian formulations to inverse problems. Despite the Bayesian motivation for these …

Model SelectionTime SeriesTime Series AnalysisUncertainty Quantification+1

Variational Regularization in Inverse Problems and Machine Learning

2021-12-08 · Martin Burger

This paper discusses basic results and recent developments on variational regularization methods, as developed for inverse problems. In a typical setup we review basic properties needed to obtain a convergent regularizat…

BIG-bench Machine Learning

Compressed Sensing MRI Reconstruction Regularized by VAEs with Structured Image Covariance

2022-10-26 · Margaret Duff, Ivor J. A. Simpson, Matthias J. Ehrhardt, Neill D. F. Campbell

Objective: This paper investigates how generative models, trained on ground-truth images, can be used \changes{as} priors for inverse problems, penalizing reconstructions far from images the generator can produce. The ai…

compressed sensingMRI Reconstruction