ML Anthology

A Bayesian Approach to Image-Based Visual Hull Reconstruction

Kristen Grauman, Gregory Shakhnarovich, Trevor Darrell
CVPR 2003 pp. 187-194
doi:10.1109/CVPR.2003.1211353 /cvpr/2003/grauman2003cvpr-bayesian/

Abstract

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.

PDF CVPR Semantic Scholar

Cite

Text

Grauman et al. "A Bayesian Approach to Image-Based Visual Hull Reconstruction." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211353

Markdown

[Grauman et al. "A Bayesian Approach to Image-Based Visual Hull Reconstruction." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/grauman2003cvpr-bayesian/) doi:10.1109/CVPR.2003.1211353

BibTeX

@inproceedings{grauman2003cvpr-bayesian,
  title     = {{A Bayesian Approach to Image-Based Visual Hull Reconstruction}},
  author    = {Grauman, Kristen and Shakhnarovich, Gregory and Darrell, Trevor},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {187-194},
  doi       = {10.1109/CVPR.2003.1211353},
  url       = {https://mlanthology.org/cvpr/2003/grauman2003cvpr-bayesian/}
}