no code implementations • 15 Jun 2022 • Cyprien Ruffino, Rachel Blin, Samia Ainouz, Gilles Gasso, Romain Hérault, Fabrice Meriaudeau, Stéphane Canu
Polarimetric imaging, along with deep learning, has shown improved performances on different tasks including scene analysis.
no code implementations • 4 Feb 2020 • Cyprien Ruffino, Romain Hérault, Eric Laloy, Gilles Gasso
We investigate the influence of this regularization term on the quality of the generated images and the fulfillment of the given pixel constraints.
1 code implementation • 2 Nov 2019 • Cyprien Ruffino, Romain Hérault, Eric Laloy, Gilles Gasso
In this paper, we study the effectiveness of conditioning GANs by adding an explicit regularization term to enforce pixel-wise conditions when very few pixel values are provided.
no code implementations • 15 May 2019 • Cyprien Ruffino, Romain Hérault, Eric Laloy, Gilles Gasso
In combination with convolutional (for the discriminator) and de-convolutional (for the generator) layers, they are particularly suitable for image generation, especially of natural scenes.
5 code implementations • 23 Jan 2019 • Yann Soullard, Cyprien Ruffino, Thierry Paquet
We report an extension of a Keras Model, called CTCModel, to perform the Connectionist Temporal Classification (CTC) in a transparent way.
1 code implementation • 21 Dec 2018 • Eric Laloy, Niklas Linde, Cyprien Ruffino, Romain Hérault, Gilles Gasso, Diedrik Jacques
Global probabilistic inversion within the latent space learned by Generative Adversarial Networks (GAN) has been recently demonstrated (Laloy et al., 2018).
Geophysics