More precisely, we show that the total variation distance and the Kullback-Leibler divergence between the generated and the data distribution are bounded from below by a constant depending on the mode separation and the Lipschitz constant.
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.
We extend recent work on the edit distance  and introduce a new metric, called the Wasserstein distance between merge trees, which is purposely designed to enable efficient computations of geodesics and barycenters.
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.
In this paper, we propose a state-of-the-art video denoising algorithm based on a convolutional neural network architecture.
Ranked #3 on Video Denoising on Set8 sigma10
Previous neural network based approaches to video denoising have been unsuccessful as their performance cannot compete with the performance of patch-based methods.
Ranked #3 on Video Denoising on DAVIS sigma30
In this work, we propose the use of a hyperprior to model image patches, in order to stabilize the estimation procedure.
This paper presents a novel unsupervised method to transfer the style of an example image to a source image.