Search Results for author:
Found 10 papers, 5 papers with code
Plug-and-Play image restoration with Stochastic deNOising REgularization
Even if they produce impressive image restoration results, these algorithms rely on a non-standard use of a denoiser on images that are less and less noisy along the iterations, which contrasts with recent algorithms based on Diffusion Models (DM), where the denoiser is applied only on re-noised images.
Convergent plug-and-play with proximal denoiser and unconstrained regularization parameter
The stepsize condition for nonconvex convergence of the proximal algorithm in use then translates to restrictive conditions on the regularization parameter of the inverse problem.
A relaxed proximal gradient descent algorithm for convergent plug-and-play with proximal denoiser
This paper presents a new convergent Plug-and-Play (PnP) algorithm.
On the potential benefits of entropic regularization for smoothing Wasserstein estimators
This paper is focused on the study of entropic regularization in optimal transport as a smoothing method for Wasserstein estimators, through the prism of the classical tradeoff between approximation and estimation errors in statistics.
Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization
Given this new result, we exploit the convergence theory of proximal algorithms in the nonconvex setting to obtain convergence results for PnP-PGD (Proximal Gradient Descent) and PnP-ADMM (Alternating Direction Method of Multipliers).
Gradient Step Denoiser for convergent Plug-and-Play
Exploiting convergence results for proximal gradient descent algorithms in the non-convex setting, we show that the proposed Plug-and-Play algorithm is a convergent iterative scheme that targets stationary points of an explicit global functional.
On the Existence of Optimal Transport Gradient for Learning Generative Models
Training of WGAN relies on a theoretical background: the calculation of the gradient of the optimal transport cost with respect to the generative model parameters.
A Generative Model for Texture Synthesis based on Optimal Transport between Feature Distributions
The GOTEX model based on patch features is also adapted to texture inpainting and texture interpolation.
Projected gradient descent for non-convex sparse spike estimation
We propose a new algorithm for sparse spike estimation from Fourier measurements.
Maximum entropy methods for texture synthesis: theory and practice
Recent years have seen the rise of convolutional neural network techniques in exemplar-based image synthesis.
