98 citations · 99 across the 4 of their papers we have counts for
4 papers
Unconditional CNN denoisers contain sparse semantic representation of images
Zahra Kadkhodaie, Stéphane Mallat, Eero Simoncelli
Generative diffusion models learn probability densities over diverse image datasets by estimating the score with a neural network trained to remove noise. Despite their remarkable…
Feature-guided score diffusion for sampling conditional densities
Zahra Kadkhodaie, Stéphane Mallat, Eero P. Simoncelli
Score diffusion methods can learn probability densities from samples. The score of the noise-corrupted density is estimated using a deep neural network, which is then used to itera…
Generalization in diffusion models arises from geometry-adaptive harmonic representations
Zahra Kadkhodaie, Florentin Guth, Eero P. Simoncelli +1
Deep neural networks (DNNs) trained for image denoising are able to generate high-quality samples with score-based reverse diffusion algorithms. These impressive capabilities seem…
New Interpretable Statistics for Large Scale Structure Analysis and Generation
E. Allys, T. Marchand, J. -F. Cardoso +3
We introduce Wavelet Phase Harmonics (WPH) statistics: interpretable low-dimensional statistics that describe 2D non-Gaussian fields. These statistics are built from WPH moments, w…