STAR-Pose: Efficient Low-Resolution Video Human Pose Estimation via Spatial-Temporal Adaptive Super-Resolution

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Yucheng, Chen, Jinyan, He, Ziyue, Han, Baojun, An, Furan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866908413279076352
author	Jin, Yucheng Chen, Jinyan He, Ziyue Han, Baojun An, Furan
author_facet	Jin, Yucheng Chen, Jinyan He, Ziyue Han, Baojun An, Furan
contents	Human pose estimation in low-resolution videos presents a fundamental challenge in computer vision. Conventional methods either assume high-quality inputs or employ computationally expensive cascaded processing, which limits their deployment in resource-constrained environments. We propose STAR-Pose, a spatial-temporal adaptive super-resolution framework specifically designed for video-based human pose estimation. Our method features a novel spatial-temporal Transformer with LeakyReLU-modified linear attention, which efficiently captures long-range temporal dependencies. Moreover, it is complemented by an adaptive fusion module that integrates parallel CNN branch for local texture enhancement. We also design a pose-aware compound loss to achieve task-oriented super-resolution. This loss guides the network to reconstruct structural features that are most beneficial for keypoint localization, rather than optimizing purely for visual quality. Extensive experiments on several mainstream video HPE datasets demonstrate that STAR-Pose outperforms existing approaches. It achieves up to 5.2% mAP improvement under extremely low-resolution (64x48) conditions while delivering 2.8x to 4.4x faster inference than cascaded approaches.
format	Preprint
id	arxiv_https___arxiv_org_abs_2506_16061
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	STAR-Pose: Efficient Low-Resolution Video Human Pose Estimation via Spatial-Temporal Adaptive Super-Resolution Jin, Yucheng Chen, Jinyan He, Ziyue Han, Baojun An, Furan Computer Vision and Pattern Recognition Human pose estimation in low-resolution videos presents a fundamental challenge in computer vision. Conventional methods either assume high-quality inputs or employ computationally expensive cascaded processing, which limits their deployment in resource-constrained environments. We propose STAR-Pose, a spatial-temporal adaptive super-resolution framework specifically designed for video-based human pose estimation. Our method features a novel spatial-temporal Transformer with LeakyReLU-modified linear attention, which efficiently captures long-range temporal dependencies. Moreover, it is complemented by an adaptive fusion module that integrates parallel CNN branch for local texture enhancement. We also design a pose-aware compound loss to achieve task-oriented super-resolution. This loss guides the network to reconstruct structural features that are most beneficial for keypoint localization, rather than optimizing purely for visual quality. Extensive experiments on several mainstream video HPE datasets demonstrate that STAR-Pose outperforms existing approaches. It achieves up to 5.2% mAP improvement under extremely low-resolution (64x48) conditions while delivering 2.8x to 4.4x faster inference than cascaded approaches.
title	STAR-Pose: Efficient Low-Resolution Video Human Pose Estimation via Spatial-Temporal Adaptive Super-Resolution
topic	Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2506.16061