DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation

2016

Conference Paper

ps


This paper considers the task of articulated human pose estimation of multiple people in real-world images. We propose an approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene, identifies occluded body parts, and disambiguates body parts between people in close proximity of each other. This joint formulation is in contrast to previous strategies, that address the problem by first detecting people and subsequently estimating their body pose. We propose a partitioning and labeling formulation of a set of body-part hypotheses generated with CNN-based part detectors. Our formulation, an instance of an integer linear program, implicitly performs non-maximum suppression on the set of part candidates and groups them to form configurations of body parts respecting geometric and appearance constraints. Experiments on four different datasets demonstrate state-of-the-art results for both single person and multi person pose estimation.

Author(s): Leonid Pishchulin and Eldar Insafutdinov and Siyu Tang and Björn Andres and Mykhaylo Andriluka and Peter Gehler and Bernt Schiele
Book Title: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Year: 2016
Month: June

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2016

Links: code
Attachments: pdf
supplementary

BibTex

@inproceedings{deepcut16cvpr,
  title = {DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation},
  author = {Pishchulin, Leonid and Insafutdinov, Eldar and Tang, Siyu and Andres, Bj{\"o}rn and Andriluka, Mykhaylo and Gehler, Peter and Schiele, Bernt},
  booktitle = { IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  month = jun,
  year = {2016},
  month_numeric = {6}
}