Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration

Bruno Lecouat 1, 2 Jean Ponce 2 Julien Mairal 1
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, Inria de Paris
Abstract : Non-local self-similarity and sparsity principles have proven to be powerful priors for natural image modeling. We propose a novel differentiable relaxation of joint sparsity that exploits both principles and leads to a general framework for image restoration which is (1) trainable end to end, (2) fully interpretable, and (3) much more compact than competing deep learning architectures. We apply this approach to denoising, jpeg deblocking, and demosaicking, and show that, with as few as 100K parameters, its performance on several standard benchmarks is on par or better than state-of-the-art methods that may have an order of magnitude or more parameters.
Complete list of metadatas

Cited literature [56 references]  Display  Hide  Download
Contributor : Bruno Lecouat <>
Submitted on : Tuesday, March 24, 2020 - 11:52:51 AM
Last modification on : Monday, March 30, 2020 - 2:38:43 PM


Files produced by the author(s)


  • HAL Id : hal-02414291, version 2



Bruno Lecouat, Jean Ponce, Julien Mairal. Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration. 2020. ⟨hal-02414291v2⟩



Record views


Files downloads