Coupling variational method with CNN for image colorization - Pierre - Workshop 1 - CEB T1 2019

Fabien Pierre (Université de Lorraine) / 04.02.2019

Coupling variational method with CNN for image colorization

Our works aim to join the powerful prediction of the convolutional neural network (CNN) with the pixel-level accuracy of variational methods. The limitations of CNN-based image colorization approaches will be described. We then focus on a CNN that is able to compute a statistical color distribution for each pixel of the image from a learning process on a large color image database. After describing its limitation, the variational method of Pierre et al. 2015 is briefly recalled. This method selects a color from a given set while regularizing the result. By combining this approach with a CNN, we have designed a fully automatic image colorization framework that improves the accuracy in comparison to CNN alone. Some numerical experiments show the accuracy provided by our method.

----------------------------------
Vous pouvez nous rejoindre sur les réseaux sociaux pour suivre nos actualités.

*************************************
Langue : Anglais; Date : 04.02.2019; Conférencier : Pierre, Fabien; Évenement : Workshop 1 - CEB T1 2019; Lieu : IHP; Mots Clés : image colorization, convolutional neural network (CNN), variational methods