no code implementations • 12 May 2022 • Robin Kips, Ruowei Jiang, Sileye Ba, Brendan Duke, Matthieu Perrot, Pietro Gori, Isabelle Bloch
In this paper we propose a novel framework based on deep learning to build a real-time inverse graphics encoder that learns to map a single example image into the parameter space of a given augmented reality rendering engine.
no code implementations • 8 Feb 2022 • Robin Kips, Panagiotis-Alexandros Bokaris, Matthieu Perrot, Pietro Gori, Isabelle Bloch
Since rendering realistic hair images requires path-tracing rendering, the conventional inverse graphics approach based on differentiable rendering is untractable.
no code implementations • 12 May 2021 • Robin Kips, Ruowei Jiang, Sileye Ba, Edmund Phung, Parham Aarabi, Pietro Gori, Matthieu Perrot, Isabelle Bloch
While makeup virtual-try-on is now widespread, parametrizing a computer graphics rendering engine for synthesizing images of a given cosmetics product remains a challenging task.
no code implementations • 12 Mar 2021 • Hugo Thimonier, Julien Despois, Robin Kips, Matthieu Perrot
When trying to independently apply image-trained algorithms to successive frames in videos, noxious flickering tends to appear.
no code implementations • 25 Aug 2020 • Julien Despois, Frederic Flament, Matthieu Perrot
Existing approaches and datasets for face aging produce results skewed towards the mean, with individual variations and expression wrinkles often invisible or overlooked in favor of global patterns such as the fattening of the face.
no code implementations • 24 Aug 2020 • Robin Kips, Pietro Gori, Matthieu Perrot, Isabelle Bloch
While existing makeup style transfer models perform an image synthesis whose results cannot be explicitly controlled, the ability to modify makeup color continuously is a desirable property for virtual try-on applications.
no code implementations • 16 Jan 2017 • Hadrien Bertrand, Matthieu Perrot, Roberto Ardon, Isabelle Bloch
Improving the model is not an easy task, due to the large number of hyper-parameters governing both the architecture and the training of the network, and to the limited understanding of their relevance.
no code implementations • 21 Jul 2014 • Mathieu Dubois, Fouad Hadj-Selem, Tommy Lofstedt, Matthieu Perrot, Clara Fischer, Vincent Frouin, Edouard Duchesnay
This algorithm uses Nesterov's smoothing technique to approximate the TV penalty with a smooth function such that the loss and the penalties are minimized with an exact accelerated proximal gradient algorithm.
3 code implementations • 2 Jan 2012 • Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Andreas Müller, Joel Nothman, Gilles Louppe, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, Édouard Duchesnay
Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems.