• Bertrand Neveu, Martin De La Gorce, Gilles Trombettoni Improving a Constraint Programming Approach for Parameter Estimation .  International Conference on Tools with Artificial Intelligence Forum 2015 PDF Simple python implementation
  • Alexandre Boulch, Martin de La Gorce, Renaud Marlet Piecewise-Planar 3D Reconstruction with Edge and Corner Regularization.  Comput. Graph. Forum 2015 PDF Data
  • Martin de La Gorce, Tomos Williams, Mike Rogers, Kevin Walker. Real-time video-based character animation.  FAA 2012
  • M. de la Gorce, N. Paragios and David Fleet. Model-based 3D Hand Pose Estimation from Monocular Video.  IEEE Transactions on Pattern Analysis & Machine Intelligence (PAMI). PDF Video
  • M. de la Gorce, Nikos Paragios . A Variational Approach to Monocular Hand-pose Estimation. Computer Vision and Image Understanding (CVIU). PDF
  • Mickael Savinaud, Martin de La Gorce, Serge Maitrejean, Nikos Paragios. M. de la Gorce, Nikos Paragios . Model-Based Multi-view Fusion of Cinematic Flow and Optical Imaging (MICCAI). PDF
  • C. Wang, M. de la Gorce and N. Paragios. Segmentation, Ordering and Multi-Object Tracking using Graphical Models. IEEE International Conference in Computer Vision (ICCV). PDF
  • M. de la Gorce, N. Paragios and David Fleet.  Model-Based Hand Tracking with Texture, Shading and Self-occlusions. IEEE Conference in Computer Vision and Pattern Recognition (CVPR), Anchorage 2008. PDF Video (codec xvid)
  • M. de la Gorce & N. Paragios. Fast Dichotomic Multiple Search Algorithm for Shortest Circular Path. 18th IARP International Conference on Pattern Recognition, (ICPR), Hong Kong 2006. PDF
  • M. de la Gorce & N. Paragios. Monocular Hand Pose Estimation Using Variable Metric Gradient-Descent. 17th British Machine Vision Conference, (BMVC), Edinburgh 2006.PDF


Thesis titled Model-based 3D hand pose estimation from monocular video, under the supervision of Nikos Paragios at Ecole Centrale de Paris.  Presented in December 2009, can be downloaded here

Reviewers : Dimitri Metaxas, Pascal Fua 
Examinators : Radu Patrice Horaud, Renaud Keriven, Adrien Bartoli, Bjorn Stenger 
Invited : David Fleet

Hand gestures play a fundamental role in inter-human communication. An efficient hand motion tracking system would provide natural ways of human-machine interaction in immersed environments. Data gloves could be use as input devices but are expensive while present hardware may inhibit free movements. Vision-based tracking in monocular video stream provides the most natural, non-invasive form of hand motion capture. However the design of an accurate and fast vision-based hand tracking is a difficult task and is an active search area. The aim of the PhD is to propose new efficient solutions for recovering 3D hand position in space and through time from the information provided by the video stream from a single camera.