| Paper: | MP-P8.12 |
| Session: | Stereoscopic and 3D Processing II: 3D Modeling & Synthesis |
| Time: | Monday, September 17, 14:30 - 17:10 |
| Presentation: |
Poster
|
| Title: |
SURFACE ESTIMATION AND TRACKING USING SEQUENTIAL MCMC METHODS FOR VIDEO BASED RENDERING |
| Authors: |
Adam Bowen; University of Warwick | | |
| | Andrew Mullins; University of Warwick | | |
| | Roland Wilson; University of Warwick | | |
| | Nasir Rajpoot; University of Warwick | | |
| Abstract: |
Video based rendering algorithms attempt to render videos of a scene from an arbitrary viewpoint, given a set of video sequences taken from several fixed viewpoints. These algorithms require either a dense camera array or some knowledge of scene structure. By applying sequential MCMC methods, we show it is possible to efficiently estimate visible surfaces. Surfaces are tracked using a particle filter which takes advantage of both frame-to-frame dependancies, and a hierarchical surface model derived from a multiresolution Gaussian mixture model analysis of the surfaces. This time-varying surface model, and the images, are input for a rendering algorithm which uses a fuzzy z-buffer and projective texturing to generate reconstructions. |
