Skip to Main content Skip to Navigation
Conference papers

Synthetic images as a regularity prior for image restoration neural networks

Abstract : Deep neural networks have recently surpassed other image restoration methods which rely on hand-crafted priors. However, such networks usually require large databases and need to be retrained for each new modality. In this paper, we show that we can reach nearoptimal performances by training them on a synthetic dataset made of realizations of a dead leaves model, both for image denoising and superresolution. The simplicity of this model makes it possible to create large databases with only a few parameters. We also show that training a network with a mix of natural and synthetic images does not affect results on natural images while improving the results on dead leaves images, which are classically used for evaluating the preservation of textures. We thoroughly describe the image model and its implementation, before giving experimental results.
Complete list of metadata
Contributor : Raphael Achddou Connect in order to contact the contributor
Submitted on : Wednesday, March 31, 2021 - 10:42:47 AM
Last modification on : Tuesday, January 18, 2022 - 3:28:05 PM
Long-term archiving on: : Thursday, July 1, 2021 - 6:15:29 PM


papier_SSVM (1).pdf
Files produced by the author(s)


  • HAL Id : hal-03186499, version 1



Raphaël Achddou, Yann Gousseau, Saïd Ladjal. Synthetic images as a regularity prior for image restoration neural networks. Eighth International Conference on Scale Space and Variational Methods in Computer Vision (SSVM)., May 2021, Cabourg (virtuel), France. ⟨hal-03186499⟩



Les métriques sont temporairement indisponibles