Accès direct au contenu

MATH

Version anglaise

aide

Accueil > Formations > Master MVA > Présentation des cours

3D computer vision

Lecturer : Pascal MONASSE, Renaud MARLET  and Mathieu AUBRY (Ecole des Ponts ParisTech)

Objective of the course :

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.

Topics :

  • 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

Prerequisites :

Linear algebra, optimization, basic programming in C, C++ or java.

Organization of courses :

  • 7x(lecture:2h, practical session:1h)

  • Usage of a personnal laptop is encouraged for practical sessions

Validation :

  • Written exam (2h)
  • Weekly reports and source code of practical sessions
  • Written exam for re-take exam (1h)

    References :

    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

    More information...