Towards Automatic Interpolation for Real and Distant Image Pairs

Maxime Lhuillier 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : Image-based rendering offers the advantage of being able to provide realistic output and at the same time to avoid the difficult problem of a complete geometric and photometric modeling of the real world. The method described here is able to deal with non rigid scenes and large camera motions. We present in this report a three step algorithm for the interpolation of two views of a scene, from which we can for instance simulated a camera motion withing the given scene. The first step establishes pixel correspondenc- es between the images and is the most difficult part. We justify the choice of region-growing based dense matching methods and we summarize their principle. Secondly, a robust algorithm converts these pixel correspondences to an adequate structure for the last step: image interpolation. This structure encompasses the transformation between the images using constrained and dependent triangulations in both of them, and handles the half-occluded areas. The implementation of the whole process is outlined and the process is demonstrated on real images.
Document type :
Reports
Complete list of metadatas

https://hal.inria.fr/inria-00073059
Contributor : Rapport de Recherche Inria <>
Submitted on : Wednesday, May 24, 2006 - 11:43:21 AM
Last modification on : Tuesday, October 9, 2018 - 9:44:16 AM
Long-term archiving on: Sunday, April 4, 2010 - 11:33:03 PM

Identifiers

  • HAL Id : inria-00073059, version 1

Collections

Citation

Maxime Lhuillier. Towards Automatic Interpolation for Real and Distant Image Pairs. RR-3619, INRIA. 1999. ⟨inria-00073059⟩

Share

Metrics

Record views

155

Files downloads

200