A Generative Model for Simultaneous Estimation of Human Body Shape and Pixel-Level Segmentation
Abstract
This paper addresses pixel-level segmentation of a human body from a single image. The problem is formulated as a multi-region segmentation where the human body is constrained to be a collection of geometrically linked regions and the background is split into a small number of distinct zones. We solve this problem in a Bayesian framework for jointly estimating articulated body pose and the pixel-level segmentation of each body part. Using an image likelihood function that simultaneously generates and evaluates the image segmentation corresponding to a given pose, we robustly explore the posterior body shape distribution using a data-driven, coarse-to-fine Metropolis Hastings sampling scheme that includes a strongly data-driven proposal term.
Cite
Text
Rauschert and Collins. "A Generative Model for Simultaneous Estimation of Human Body Shape and Pixel-Level Segmentation." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33715-4_51Markdown
[Rauschert and Collins. "A Generative Model for Simultaneous Estimation of Human Body Shape and Pixel-Level Segmentation." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/rauschert2012eccv-generative/) doi:10.1007/978-3-642-33715-4_51BibTeX
@inproceedings{rauschert2012eccv-generative,
title = {{A Generative Model for Simultaneous Estimation of Human Body Shape and Pixel-Level Segmentation}},
author = {Rauschert, Ingmar and Collins, Robert T.},
booktitle = {European Conference on Computer Vision},
year = {2012},
pages = {704-717},
doi = {10.1007/978-3-642-33715-4_51},
url = {https://mlanthology.org/eccv/2012/rauschert2012eccv-generative/}
}