“Obtaining 3D Models With a Hand-Held Camera” by Pollefeys

  • ©Marc Pollefeys

Conference:


Entry Number: 02

Title:

    Obtaining 3D Models With a Hand-Held Camera

Course Organizer(s):



Presenter(s):



Abstract:


    Prerequisites
    This tutorial is accessible to a wide audience with diverse backgrounds. It requires basic understanding of 3D geometry and perspective projection. A full appreciation of the course requires some knowledge of projective geometry, computer vision, and image-processing techniques.

    Topics
    Feature point extraction and matching, multi-view relations, robust matching, projective structure and motion recovery, self-calibration, bundle adjustment, image-pair rectification, dense stereo matching, multi-view matching, 3D surface modeling, and applications.

    Description
    How 3D models can be obtained from images acquired with a hand-held camera. The approach is based on advanced automatic techniques that avoid camera calibration and a priori scene knowledge, which gradually retrieve more and more information about the image, the cameras, and the scene. Applications range from archaeology to planetary exploration.

     


Type: