Smooth Kernel Density Estimate for Multiple View Reconstruction. Ruttle, J., Manzke, M., & Dahyot, R. In proceedings of The 7th European Conference for Visual Media Production, CVMP 2010, pages 74 -81, 17 - 18 November, 2010.
doi  abstract   bibtex   
We present a statistical framework to merge the information from silhouettes segmented in multiple view images to infer the 3D shape of an object. The approach is generalising the robust but discrete modelling of the visual hull by using the concept of averaged likelihoods. One resulting advantage of our framework is that the objective function is continuous and therefore an iterative gradient ascent algorithm can be defined to efficiently search the space. Moreover this results in a method which is less memory demanding and one that is very suitable to a parallel processing architecture. Experimental results shows that this approach is efficient for getting a robust initial guess to the 3D shape of an object in view.
@inproceedings{Ruttle2010CVMP, 
title= {Smooth Kernel Density Estimate for Multiple View Reconstruction}, 
author= {J. Ruttle and M. Manzke and R. Dahyot},
 booktitle= {proceedings of The 7th European Conference for Visual Media Production, CVMP 2010}, 
 location= {London UK}, month= {17 - 18 November}, 
 pages= {74 -81}, 
 year= {2010},
 abstract={We present a statistical framework to merge the information from silhouettes segmented in multiple view images to infer the 3D shape of an object. 
 The approach is generalising the robust but discrete modelling of the visual hull by using the concept of averaged likelihoods.
 One resulting advantage of our framework is that the objective function is continuous and therefore an iterative gradient ascent algorithm
 can be defined to efficiently search the space. Moreover this results in a method which is less memory demanding and one that is very suitable 
 to a parallel processing architecture.
 Experimental results shows that this approach is efficient for getting a robust initial guess to the 3D shape of an object in view.},
 doi= {10.1109/CVMP.2010.17}}

Downloads: 0