The preprint of our upcoming IEEE Trans. PAMI on scene labeling is available. We use a multi-scale convolutional network trained in supervised mode on fully-labeled images in which each pixel is labeled by the category of the object it belongs to. A simple superpixel-based post-processing smoothes out the output labels and lines up the segment boundaries with image contours.
The method significantly improves the state of the art for accuracy on three common dataset: Stanford Background (8 classes), SIFT Flow (33 classes) and Barcelona (170 classes).
The method is also roughly 100 times faster than the best competitor: roughly 0.5 second per frame on a 4-core laptop. An FPGA implementation of the system (based on the NeuFlow architecture) runs the bulk of the algorithm in 50 ms at 1280x240 resolution, using about 10 Watts of power.
It is available here.
On the 4th of December 2016, Hugues Talbot and myself gave a tutorial on graph-based morphology at ICPR. This tutorial follows the outline of the PRL survey paper on Graph-Based Morphology. Slides of the talk and videos are available on a dedicated page. 
A second PAMI paper on the shape-based morphological filtering framework, has been accepted. This one is dedicated to the hierchical segmentation. Of course, the first PAMI on the topic is still available. My p
aper on ultrametric watersheds is amongst the selected 5 top-cited articles from the Journal of Mathematical Imaging and Vision available free until the end of September.
More information in the Springer NewsLetter
The paper is avalable here. This HAL version will be forever freely available.
Our paper on Dual-Constrained Total Variation on Graphs has been accepted to SIAM Journal on Imaging Siences. Preprint is available, as well as source code. 
ith Pascal Romon , we are organizing a colloquium on Discrete Curvature. The aim of this meeting is to bring together researchers from diverse backgrounds (including mathematics and computer science) on the common theme of discrete curvature and to make an update on the many achievements of the last decade. We want to promote interaction between various fields, so topics and participants can and should be varied, as long as they fit under the under the main theme. Prestigious speakers are already programmed.
Another prize for Camille Couprie! She has just been awarded an accessit for the prestigious Gilles Khan prize.
Congratulations, Camille!
Prix EADS de la meilleure thèse interdisciplinaire : Camille COUPRIE pour ses travaux sur l' « Optimisation variationnelle discrète et applications en vision par ordinateur », ED 532 - MSTIC. 
The challenge was held on October 1st, 2012 in Nice Sophia Antipolis, Côte d'Azur, France, at the workshop 3D Cardiovascular Imaging: a MICCAI segmentation challenge at the 15th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 
Our special issue is now available on IEEE Xplore. You can see this at:The preprint of our upcoming IEEE Trans. PAMI on scene labeling is available. We use a multi-scale convolutional network trained in supervised mode on fully-labeled images in which each pixel is labeled by the category of the object it belongs to. A simple superpixel-based post-processing smoothes out the output labels and lines up the segment boundaries with image contours. 
My name is Laurent Najman and I am a Professor at Université Paris-Est, LIGM, ESIEE.
You can contact me through the Form on the right.
Idea and Design by idea arts
Shape based filtering
Non-Local Dual Constrained Total Variation Denoising (NL-DCTV)
Saliency maps
Scene parsing with hierarchical convolutional nets
The Polygonal Path Image (PPI)