DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model
Authors:
Preprint
Abstract
The goal of this paper is to advance the state-of-the-art of articulated pose estimation in scenes with multiple people. To that end we contribute on three fronts. We propose (1) improved body part detectors that generate effective bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms that allow to assemble the proposals into a variable number of consistent body part configurations; and (3) an incremental optimization strategy that explores the search space more efficiently thus leading both to better performance and significant speed-up factors. Evaluation is done on two single-person and two multi-person pose estimation benchmarks. The proposed approach significantly outperforms best known multi-person pose estimation results while demonstrating competitive performance on the task of single person pose estimation. Models and code available at http://pose.mpi-inf.mpg.deKeywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Pose Machines: Articulated Pose Estimation via Inference Machines2014
- Human Pose Estimation Using a Joint Pixel-wise and Part-wise Formulation2013
- Articulated Pose Estimation Using Discriminative Armlet Classifiers2013
- MODEC: Multimodal Decomposable Models for Human Pose Estimation2013
- Discriminative Appearance Models for Pictorial StructuresInternational Journal of Computer Vision, 2011
- Learning effective human pose estimation from inaccurate annotation2011
- Improved Human Parsing with a Full Relational Model2010
- We Are Family: Joint Pose Estimation of Multiple Persons2010
- Global pose estimation using non-tree models2008
- Correlation clustering in general weighted graphsTheoretical Computer Science, 2006