1 code implementation • 11 Aug 2010 • Stefan Sommer, François Lauze, Mads Nielsen
In fields ranging from computer vision to signal processing and statistics, increasing computational power allows a move from classical linear models to models that incorporate non-linear phenomena.
Computational Geometry
no code implementations • 4 Jul 2017 • Yvain Quéau, Bastien Durix, Tao Wu, Daniel Cremers, François Lauze, Jean-Denis Durou
The second one directly recovers the depth, by formulating photometric stereo as a system of PDEs which are partially linearized using image ratios.
no code implementations • 10 Jul 2017 • Marco Loog, François Lauze
We start out by demonstrating that an elementary learning task, corresponding to the training of a single linear neuron in a convolutional neural network, can be solved for feature spaces of very high dimensionality.
1 code implementation • 28 May 2019 • Henrik Grønholt Jensen, François Lauze, Sune Darkner
We present an information-theoretic approach to the registration of images with directional information, and especially for diffusion-Weighted Images (DWI), with explicit optimization over the directional scale.