@inproceedings{25fa47d985ff46cea2b7e2c6b75efed8,
title = "POSERN: A 2D POSE REFINEMENT NETWORK FOR BIAS-FREE MULTI-VIEW 3D HUMAN POSE ESTIMATION",
abstract = "We propose a new 2D pose refinement network that learns to predict the human bias in the estimated 2D pose. There are biases in 2D pose estimations that are due to differences between annotations of 2D joint locations based on annotators{\textquoteright} perception and those defined by motion capture (MoCap) systems. These biases are crafted into publicly available 2D pose datasets and cannot be removed with existing error reduction approaches. Our proposed pose refinement network allows us to efficiently remove the human bias in the estimated 2D poses and achieve highly accurate multi-view 3D human pose estimation.",
author = "Akihiko Sayo and Diego Thomas and Hiroshi Kawasaki and Yuta Nakashima and Katsushi Ikeuchi",
note = "Funding Information: This work was supported by JSPS/KAKENHI 20H00611, 18K19824, 18H04119 in Japan. Publisher Copyright: {\textcopyright} 2021 IEEE; 2021 IEEE International Conference on Image Processing, ICIP 2021 ; Conference date: 19-09-2021 Through 22-09-2021",
year = "2021",
doi = "10.1109/ICIP42928.2021.9506022",
language = "English",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "3233--3237",
booktitle = "2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings",
address = "United States",
}