Prè-requis
Linear algebra, optimization, basic programming in C, C++ or java.
Objectif du cours
Explore the theoretical foundations of 3D computer vision from multiple views, with emphasis on binocular stereo, and show the practical limitations in the algorithmic state of the art.
Présentation : here
Organisation des séances
- 6 lectures of 3h , one session for the exam
- Usage of a personnal laptop is encouraged for practical sessions
Mode de validation
- Written exam
- Weekly reports and source code of practical sessions
- Written exam for re-take exam
Références
R. Hartley and A. Zisserman, Mutiple View Geometry in Computer Vision, 2nd edition, Cambridge University Press
R. Szeliski, Computer Vision: Algorithms and Applications, Springer, 2011
Thèmes abordés
- Camera geometry, panorama construction
- Calibration, projection matrix
- Interest points, including SIFT, matching
- Essential and fundamental matrices, RANSAC algorithm
- Disparity maps with local methods and filtering
- Disparity maps with global methods, graph cuts
- Multiple view stereo
Les intervenants
Pascal MONASSE
(Ecole des Ponts ParisTech)
Mathieu AUBRY
(Ecole des Ponts ParisTech)