Human Pose Estimation from an Extremely Low-Resolution Image Sequence by Pose Transition Embedding Network

Yasutomo Kawanishi, Hitoshi Nishimura, Hiroshi Murase

2025

Abstract

This paper addresses the problem of human pose estimation from an extremely low-resolution (ex-low) image sequence. In an ex-low image (e.g., 16 × 16 pixels), it is challenging, even for human beings, to estimate the human pose smoothly and accurately only from a frame because of resolution and noise. This paper proposes a human pose estimation method, named Pose Transition Embedding Network, that considers the temporal continuity of human pose transition by using a pose-embedded manifold. This method first builds a pose transition manifold from the ground truth of human pose sequences to learn feasible pose transitions using an encoder-decoder model named Pose Transition Encoder-Decoder. Then, an image encoder, named Ex-Low Image Encoder Transformer, encodes an ex-low image sequence into an embedded vector using a transformer-based network. Finally, the estimated human pose is reconstructed using a pose decoder named Pose Transition Decoder. The performance of the method is confirmed by evaluating an ex-low human pose dataset generated from a publicly available action recognition dataset.

Paper Citation

in Harvard Style

Kawanishi Y., Nishimura H. and Murase H. (2025). Human Pose Estimation from an Extremely Low-Resolution Image Sequence by Pose Transition Embedding Network. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 478-485. DOI: 10.5220/0013239600003912

in Bibtex Style

@conference{visapp25,
author={Yasutomo Kawanishi and Hitoshi Nishimura and Hiroshi Murase},
title={Human Pose Estimation from an Extremely Low-Resolution Image Sequence by Pose Transition Embedding Network},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={478-485},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013239600003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Human Pose Estimation from an Extremely Low-Resolution Image Sequence by Pose Transition Embedding Network
SN - 978-989-758-728-3
AU - Kawanishi Y.
AU - Nishimura H.
AU - Murase H.
PY - 2025
SP - 478
EP - 485
DO - 10.5220/0013239600003912
PB - SciTePress