This course focuses on the recovery of the 3D structure of a scene from its 2D images. In particular, we are interested in the 3D reconstruction of a rigid scene from images taken by a stationary camera (same viewpoint). This problem is interesting as we want the multiple images of the scene to capture complementary information despite the fact that the scene is rigid and the camera is fixed. To this end, we explore several ways of capturing images where each image provides additional information about the scene.
Offert par


À propos de ce cours
Students should know the fundamentals of linear algebra and calculus. The knowledge of any programming language is beneficial, though not required.
Ce que vous allez apprendre
Learn radiometric concepts related to light and how it interacts with scenes.
Understand reflectance models and the different physical mechanisms that determine the appearance of a surface.
Develop a method for recovering the shape of a surface from its shading.
Understand the principle of photometric stereo where a dense surface normal map of the scene is obtained by varying the illumination direction.
Compétences que vous acquerrez
- Photometric Stereo
- Depth from Focus and Defocus
- Structed Light Methods
- Reflectance Models
- Radiometry
Students should know the fundamentals of linear algebra and calculus. The knowledge of any programming language is beneficial, though not required.
Offert par

Université Columbia
For more than 250 years, Columbia has been a leader in higher education in the nation and around the world. At the core of our wide range of academic inquiry is the commitment to attract and engage the best minds in pursuit of greater human understanding, pioneering new discoveries and service to society.
Programme de cours : ce que vous apprendrez dans ce cours
Getting Started: 3D Reconstruction - Single Viewpoint
Radiometry and Reflectance
Photometric Stereo
Shape from Shading
À propos du Spécialisation First Principles of Computer Vision
This specialization presents the first comprehensive treatment of the foundations of computer vision. It focuses on the mathematical and physical underpinnings of vision and has been designed for learners, practitioners and researchers who have little or no knowledge of computer vision. The program includes a series of 5 courses. Any learner who completes this specialization has the potential to build a successful career in computer vision, a thriving field that is expected to increase in importance in the coming decades.

Foire Aux Questions
Quand aurai-je accès aux vidéos de cours et aux devoirs ?
À quoi ai-je droit si je m'abonne à cette Spécialisation ?
Une aide financière est-elle possible ?
D'autres questions ? Visitez le Centre d'Aide pour les Étudiants.