no code implementations • 12 Dec 2023 • Matthieu Terris, Chao Tang, Adrian Jackson, Yves Wiaux
In a previous work, we introduced a class of convergent PnP algorithms, dubbed AIRI, relying on a forward-backward algorithm, with a differentiable data-fidelity term and dynamic range-specific denoisers trained on highly pre-processed unrelated optical astronomy images.
no code implementations • 4 Dec 2023 • Matthieu Terris, Thomas Moreau, Nelly Pustelnik, Julian Tachella
Plug-and-play algorithms constitute a popular framework for solving inverse imaging problems that rely on the implicit definition of an image prior via a denoiser.
no code implementations • 30 Nov 2023 • Matthieu Terris, Thomas Moreau
They are typically trained for a specific task, with a supervised loss to learn a mapping from the observations to the image to recover.
no code implementations • 28 Oct 2022 • Amir Aghabiglou, Matthieu Terris, Adrian Jackson, Yves Wiaux
We propose a residual DNN series approach, also interpretable as a learned version of matching pursuit, where the reconstructed image is a sum of residual images progressively increasing the dynamic range, and estimated iteratively by DNNs taking the back-projected data residual of the previous iteration as input.
no code implementations • 25 Feb 2022 • Matthieu Terris, Arwa Dabbech, Chao Tang, Yves Wiaux
The approach consists in learning a prior image model by training a deep neural network (DNN) as a denoiser, and substituting it for the handcrafted proximal regularization operator of an optimization algorithm.
2 code implementations • 24 Dec 2020 • Jean-Christophe Pesquet, Audrey Repetti, Matthieu Terris, Yves Wiaux
Recently, several works have proposed to replace the operator related to the regularization by a more sophisticated denoiser.
Automated Theorem Proving Image Restoration Optimization and Control Image and Video Processing 47H05, 90C25, 90C59, 65K10, 49M27, 68T07, 68U10, 94A08