Image interpolation by joint view triangulation
- 23 June 1999
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 139-145
- https://doi.org/10.1109/cvpr.1999.784621
Abstract
International audienceCreating novel views by interpolating prestored images or view morphing has many applications in visual simulation. We present in this paper a new method of automatically interpolating two images which tackles two most difficult problems of morphing due to the lack of depth information: pixel matching and visibility handling. We first describe a quasi-dense matching algorithm based on region growing with the best first strategy for match propagation. Then, we describe a robust construction of matched planar patches using local geometric constraints encoded by a homography. After that we introduce a novel representation?joint view triangulation?for visible and half-occluded patches in two images to handle their visibility during the creation of new view. Finally we demonstrate these techniques on real image pairsKeywords
This publication has 18 references indexed in Scilit:
- The lumigraphPublished by Association for Computing Machinery (ACM) ,1996
- Light field renderingPublished by Association for Computing Machinery (ACM) ,1996
- Image Morphing Using Deformation TechniquesThe Journal of Visualization and Computer Animation, 1996
- QuickTime VRPublished by Association for Computing Machinery (ACM) ,1995
- View interpolation for image synthesisPublished by Association for Computing Machinery (ACM) ,1993
- Minimal roughness property of the Delaunay triangulationComputer Aided Geometric Design, 1990
- ‘Region-growing’ algorithm for matching of terrain imagesImage and Vision Computing, 1989
- Structure from stereo-a reviewIEEE Transactions on Systems, Man, and Cybernetics, 1989
- A Combined Corner and Edge DetectorPublished by British Machine Vision Association and Society for Pattern Recognition ,1988
- Computational GeometryPublished by Springer Nature ,1985