Bootstrapping Human Optical Flow and Pose
Aritro Roy Arko (The University of British Columbia),* Jim Little (University of British Columbia, Canada), Kwang Moo Yi (University of British Columbia)
The 33rd British Machine Vision Conference
Abstract
We propose a bootstrapping framework to enhance human optical flow and pose. We show that, for videos involving humans in scenes, we can improve both the optical flow and the pose estimation quality of humans by considering the two tasks at the same time. We enhance optical flow estimates by fine-tuning them to fit the human pose estimates and vice versa. In more detail, we optimize the pose and optical flow networks to, at inference time, agree with each other. We show that this results in state-of-the-art results on the Human 3.6M and 3D Poses in the Wild datasets, as well as a human-related subset of the Sintel dataset, both in terms of pose estimation accuracy and the optical flow accuracy at human joint locations. Code available at https://github.com/ubc-vision/bootstrapping-human-optical-flow-and-poseVideo
Citation
@inproceedings{Arko_2022_BMVC,
author = {Aritro Roy Arko and Jim Little and Kwang Moo Yi},
title = {Bootstrapping Human Optical Flow and Pose},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0139.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by