no code implementations • 29 Apr 2022 • Rita Fermanian, Mikael Le Pendu, Christine Guillemot
We show that it is possible to train a network directly modeling the gradient of a MAP regularizer while jointly training the corresponding MAP denoiser.
no code implementations • 1 Oct 2021 • Mikael Le Pendu, Christine Guillemot
Plug-and-Play optimization recently emerged as a powerful technique for solving inverse problems by plugging a denoiser into a classical optimization algorithm.
no code implementations • 21 Jan 2019 • Mikael Le Pendu, Christine Guillemot, Aljosa Smolic
In this paper, we present a new Light Field representation for efficient Light Field processing and rendering called Fourier Disparity Layers (FDL).