We present a Bayesian approach to image-based visual hull reconstruction. The 3D (three-dimensional) shape of an object of a known class is represented by sets of silhouette views simultaneously observed from multiple cameras. We show how the use of a class-specific prior in a visual hull reconstruction can reduce the effect of segmentation errors from the silhouette extraction process. In our representation, 3D information is implicit in the joint observations of multiple contours from known viewpoints. We model the prior density using a probabilistic principal components analysis-based technique and estimate a maximum a posteriori reconstruction of multi-view contours. The proposed method is applied to a dataset of pedestrian images, and improvements in the approximate 3D models under various noise conditions are shown.
A Bayesian approach to image-based visual hull reconstruction
2003-01-01
789443 byte
Conference paper
Electronic Resource
English
A Bayesian Approach to Image-Based Visual Hull Reconstruction
British Library Conference Proceedings | 2003
|A MCMC Approach for Bayesian Super-Resolution Image Reconstruction
British Library Conference Proceedings | 2005
|Visual Hull Construction Using Adaptive Sampling
IEEE | 2005
|Algebraic solution for the visual hull
IEEE | 2004
|