Welcome

I am assistant professor of Computer Science at the Ensimag (School of Computer Science and Applied Mathematics, INP Grenoble University), and a researcher at the INRIA Grenoble Rhône-Alpes, France, with the Morpheo team since 2011.

 

I obtained my PhD from the Institut National Polytechnique de Grenoble in 2005 with the INRIA MOVI team. I started my professional career as a postdoctoral research assistant at the University of North Carolina's Computer Vision Group in 2006, and as assistant professor at the University of Bordeaux, with the IPARLA team, INRIA Bordeaux Sud-Ouest. My expertise and interest is in the field of computer vision, dynamic 3D modeling and 4D spatio-temporal modeling from multiple views, 3D interaction. Full CV available.

 

News

 

Research Interests

 

4D Temporal Alignment and Shape Tracking
Estimation of Human Body Shape in Motion with Wide Clothing

Tracking Under Clothing

Volumetric 3D Tracking by Detection
Volume Tracking by Detection
An Efficient Volumetric Framework for Shape Tracking
Volumetric Shape Tracking
Deformable Shape Analysis
On Mean Pose and Variability of 3D Deformable Models
Mean Pose and Non-rigid Motion Detection
Learning Temporally Consistent Rigidities
Temporal Non-Rigid Segmentation
Multi-View Segmentation
N-Tuple Color Segmentation for Multi-View Silhouette Extraction
N-Tuple Color Multi-View Segmentation
Multi-View Object Segmentation in Space and Time
Space-Time Multi-View Segmentation
Temporal Appearance Representations and Superresolution

High Resolution 3D Shape Texture from Multiple Videos

High Resolution 3D Shape Texture from Multiple Videos
Fast Booleans on Meshes
Efficient Polyhedral Modeling from Silhouettes

QuickCSG: Fast Variadic Polyhedral Booleans

Efficient Silhouette-based Modeling
Efficient Polyhedral Modeling from Silhouettes
EPVH - Polyhedral Visual Hulls
Visual Shapes of Silhouette Sets

 

Probabilistic Occupancy Analysis

Fusion of Multi-View Silhouette Cues Using a Space Occupancy Grid

Multi-View Silhouette Fusion
3D Occlusion Inference from Silhouette Cues
3D Occlusion Inference from Silhouette Cues

 

Scene Flow
Surface Flow from Visual Cues
Surface Flow from Visual Cues
Probabilistic 3D Occupancy Flow with Latent Silhouette Cues
Probabilistic 3D Occupancy Flow
Interactive Vision Systems
Multicamera Real-Time 3D Modeling for Telepresence and Remote Collaboration

3D Telepresence with Multi-Camera Systems

The GrImage Platform: A Mixed Reality Environment for Interactions

GrImage: Mixed Reality Interaction

QuickCSG

We are releasing binaries of our new software, QuickCSG, which can compute visual hulls as well as arbitrary boolean combinations on N polyhedral solids. Current tests on our 68-camera Kinovis platform show that QuickCSG outperforms our previous visual hull computation software EPVH by a factor of 20x on 40 cameras or more. Our experimental tests also show that QuickCSG significantly outperforms all currently known available boolean CSG codes in terms of speed on two or more inputs. A publication is currently submitted for review but a preliminary version is available as research report.

 

EPVH

EPVH is one of the projects developed during my thesis. I receive a number of requests for providing the code or binary. I can no longer distribute either, as EPVH is now exclusively distributed by 4DViews, and built-in 4DViews software suites. If you have datasets on which you would like to perform comparisons with EPVH for research purposes, I can process them and provide the resulting data for static objects or sequences. However, you are encouraged to use QuickCSG instead, which significantly outperforms EPVH.