Search Results for author:
Found 19 papers, 10 papers with code
Infusion: Internal Diffusion for Video Inpainting
We show that in the case of video inpainting, thanks to the highly auto-similar nature of videos, the training of a diffusion model can be restricted to the video to inpaint and still produce very satisfying results.
Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
Posterior sampling has been shown to be a powerful Bayesian approach for solving imaging inverse problems.
Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution
Our method alternates between approximating the expected log-likelihood of the inverse problem using samples drawn from a diffusion model and a maximization step to estimate unknown model parameters.
Inverse problem regularization with hierarchical variational autoencoders
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.
Provably Convergent Plug & Play Linearized ADMM, applied to Deblurring Spatially Varying Kernels
Plug & Play methods combine proximal algorithms with denoiser priors to solve inverse problems.
Video Restoration with a Deep Plug-and-Play Prior
Under a Bayesian formalism, the method consists in using a deep convolutional denoising network in place of the proximal operator of the prior in an alternating optimization scheme.
Diverse super-resolution with pretrained deep hiererarchical VAEs
We investigate the problem of producing diverse solutions to an image super-resolution problem.
Deep Model-Based Super-Resolution with Non-uniform Blur
Instead, in this paper, we address the more realistic and computationally challenging case of spatially-varying blur.
Patch-Based Stochastic Attention for Image Editing
We refer to our proposed layer as a "Patch-based Stochastic Attention Layer" (PSAL).
On Maximum-a-Posteriori estimation with Plug & Play priors and stochastic gradient descent
Bayesian methods to solve imaging inverse problems usually combine an explicit data likelihood function with a prior distribution that explicitly models expected properties of the solution.
Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie
The proposed algorithms are demonstrated on several canonical problems such as image deblurring, inpainting, and denoising, where they are used for point estimation as well as for uncertainty visualisation and quantification.
Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
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.
Learning local regularization for variational image restoration
In this work, we propose a framework to learn a local regularization model for solving general image restoration problems.
Multi-Task Learning of Height and Semantics from Aerial Images
Aerial or satellite imagery is a great source for land surface analysis, which might yield land use maps or elevation models.
Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior
In this paper we address the problem of solving ill-posed inverse problems in imaging where the prior is a neural generative model.
Processsing Simple Geometric Attributes with Autoencoders
This results in a wide range of practical problems, such as difficulties in training, the tendency to sample images with little or no variability, and generalisation problems.
Deep Depth from Defocus: how can defocus blur improve 3D estimation using dense neural networks?
We also investigate the influence of blur on depth prediction observing model uncertainty with a Bayesian neural network approach.
A Bayesian Hyperprior Approach for Joint Image Denoising and Interpolation, with an Application to HDR Imaging
In this work, we propose the use of a hyperprior to model image patches, in order to stabilize the estimation procedure.
Video Inpainting of Complex Scenes
Our algorithm is able to deal with a variety of challenging situations which naturally arise in video inpainting, such as the correct reconstruction of dynamic textures, multiple moving objects and moving background.
