14 March 2005 View morphing and interpolation through triangulation
Author Affiliations +
This paper presents a method for view morphing and interpolation based on triangulation. View morphing here is viewed here as a basic tool for view interpolation. The feature points in each source image are first detected. Based on these feature points, each source image is segmented into a set of triangular regions and local affine transformations are then used for texture mapping of each triangle from the source image to the destination image. This is called triangulation-based texture mapping. However, one of the significant problems associated with this approach is texture discontinuity between adjacent triangles. In order to solve this problem, the triangular patches that might cause these adjacent discontinuities are first detected and the optimal affine transformations for these triangles are then applied. In the subsequent view interpolation step, all source images are transferred to the novel view through view morphing, and the final novel view is the combination of all these candidate novel views. The major improvement over the traditional approach is a feedback-based method proposed to determine the weights for the texture combination from different views. Simulation results show that our method can reduce the discontinuities in triangle-based view morphing and significantly improve the quality of the interpolated views.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiaoyong Sun, Xiaoyong Sun, Eric Dubois, Eric Dubois, } "View morphing and interpolation through triangulation", Proc. SPIE 5685, Image and Video Communications and Processing 2005, (14 March 2005); doi: 10.1117/12.586915; https://doi.org/10.1117/12.586915


Reduced depth of field using multi-image fusion
Proceedings of SPIE (March 06 2013)
Vehicle feature extraction by patch-based sampling
Proceedings of SPIE (May 06 2003)
Visualization of adaptive mesh refinement data
Proceedings of SPIE (May 02 2001)
3D virtual colonoscopy with real-time volume rendering
Proceedings of SPIE (April 19 2000)
Object based very low bit rate coding with robust global...
Proceedings of SPIE (September 15 1996)
Colour cluster analysis for pigment identification
Proceedings of SPIE (February 28 2008)

Back to Top