Help Privacy Policy Disclaimer
  Advanced SearchBrowse




Conference Paper

Correspondence Analysis Between The Image Formation Pipelines of Graphics and Vision


Li,  Ming
Computer Graphics, MPI for Informatics, Max Planck Society;
Graphics - Optics - Vision, MPI for Informatics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available

Li, M. (2001). Correspondence Analysis Between The Image Formation Pipelines of Graphics and Vision. In S. J. Salvador, & P. Filiberto (Eds.), Proceedings of the IX Spanish Symposium on Pattern Recognition and Image Analysis (pp. 187-192). Castellón, Spain: Publications de la Universitat Jaume I.

Cite as: https://hdl.handle.net/11858/00-001M-0000-000F-3276-B
Augmented Reality can merge the computer-generated objects into the real image or video sequences, one key issue is to keep the geometric consistency between the real and virtual objects. This is achieved by using the camera parameters recovered from the real image to render the virtual objects. Camera parameters' recovery is a basic problem in the area of computer vision. On the other hand, rendering is the major concern of computer graphics. Ususally in these two areas different image formation pipelines are used. This paper presents a side-by-side comparison between the pipelines, in order to make it easier to setup the recovered camera parameters to do the rendering for AR applications. Some experiment results are shown to verify the correctness of the analysis.