Computer Graphics
TU Braunschweig

Reconstruction of Dense Correspondences


Reconstruction of Dense Correspondences

Images are the basic input for a vast majority of algorithms dealing with the reconstruction of the real world. To analyze a scene from a collection of images it becomes inevitable to put these images into correspondence. These correspondences then form the basis for many subsequent analyses, including camera calibration, stereo and 3D reconstruction, motion information, scene flow and others. While some of these tasks like camera calibration require only sparse correspondences between the images others require per-pixel correspondence, also known as dense correspondence estimation.

This chapter gives a hands-on guide on how to compute dense correspondences between images.


Author(s):Martin Eisemann, Jan-Michael Frahm, Yannick Remion, Muhannad Ismael
Published:May 2015
Type:Book chapter
Book:Digital Representations of the Real World: How to Capture, Model, and Render Visual Reality (CRC Press)
ISBN:9781482243819
Project(s): Digital Representations of the Real World  Reality CG 

BibTex PDF 



@incollection{Eisemann2015RDC,
  title = {Reconstruction of Dense Correspondences},
  author = {Eisemann, Martin and Frahm, Jan-Michael and Remion, Yannick and Ismael, Muhannad},
  booktitle = {Digital Representations of the Real World: How to Capture, Model, and Render Visual Reality},
  isbn = {9781482243819},
  publisher = {{CRC} Press},
  editor = {Marcus A. Magnor, Oliver Grau, Olga Sorkine-Hornung, Christian Theobalt},
  chapter = {8},
  pages = {113--133},
  month = {May},
  year = {2015}
}

Authors