Predicting 3D people from 2D pictures
2006
Conference Paper
ps
We propose a hierarchical process for inferring the 3D pose of a person from monocular images. First we infer a learned view-based 2D body model from a single image using non-parametric belief propagation. This approach integrates information from bottom-up body-part proposal processes and deals with self-occlusion to compute distributions over limb poses. Then, we exploit a learned Mixture of Experts model to infer a distribution of 3D poses conditioned on 2D poses. This approach is more general than recent work on inferring 3D pose directly from silhouettes since the 2D body model provides a richer representation that includes the 2D joint angles and the poses of limbs that may be unobserved in the silhouette. We demonstrate the method in a laboratory setting where we evaluate the accuracy of the 3D poses against ground truth data. We also estimate 3D body pose in a monocular image sequence. The resulting 3D estimates are sufficiently accurate to serve as proposals for the Bayesian inference of 3D human motion over time
Award: | (Best Paper) |
Author(s): | Sigal, L. and Black, M. J. |
Book Title: | Proc. IV Conf. on Articulated Motion and DeformableObjects (AMDO) |
Volume: | LNCS 4069 |
Pages: | 185--195 |
Year: | 2006 |
Month: | July |
Department(s): | Perzeptive Systeme |
Bibtex Type: | Conference Paper (inproceedings) |
Paper Type: | Conference |
DOI: | 10.1007/11789239_19 |
Award Paper: | Best Paper |
Links: |
pdf
pdf from publisher Video |
Video: | |
BibTex @inproceedings{Sigal:AMDO:2006, title = {Predicting {3D} people from {2D} pictures}, author = {Sigal, L. and Black, M. J.}, booktitle = {Proc. IV Conf. on Articulated Motion and DeformableObjects (AMDO)}, volume = {LNCS 4069}, pages = {185--195}, month = jul, year = {2006}, doi = {10.1007/11789239_19}, month_numeric = {7} } |