Our work introduces a novel way to increase pose estimation accuracy by discovering parts from unannotated regions of training images. Discovered parts are used to generate more accurate appearance likelihoods for traditional part-based models like Pictorial Structures [13] and its derivatives. Our experiments on images of a hawkmoth in flight show that our proposed approach significantly improves over existing work [27] for this application, while also being more generally applicable. Our proposed approach localizes landmarks at least twice as accurately as a baseline based on a Mixture of Pictorial Structures (MPS) model. Our unique High-Resolution Moth Flight (HRMF) dataset is made publicly available with annotations.
@article{arxiv.1605.00707,
title = {Discovering Useful Parts for Pose Estimation in Sparsely Annotated Datasets},
author = {Mikhail Breslav and Tyson L. Hedrick and Stan Sclaroff and Margrit Betke},
journal= {arXiv preprint arXiv:1605.00707},
year = {2016}
}