Robust Low-Light Human Pose Estimation through Illumination-Texture Modulation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Feng, Li, Ze, Zhu, Xiatian, Chen, Lei
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913649300340736
author Zhang, Feng
Li, Ze
Zhu, Xiatian
Chen, Lei
author_facet Zhang, Feng
Li, Ze
Zhu, Xiatian
Chen, Lei
contents As critical visual details become obscured, the low visibility and high ISO noise in extremely low-light images pose a significant challenge to human pose estimation. Current methods fail to provide high-quality representations due to reliance on pixel-level enhancements that compromise semantics and the inability to effectively handle extreme low-light conditions for robust feature learning. In this work, we propose a frequency-based framework for low-light human pose estimation, rooted in the "divide-and-conquer" principle. Instead of uniformly enhancing the entire image, our method focuses on task-relevant information. By applying dynamic illumination correction to the low-frequency components and low-rank denoising to the high-frequency components, we effectively enhance both the semantic and texture information essential for accurate pose estimation. As a result, this targeted enhancement method results in robust, high-quality representations, significantly improving pose estimation performance. Extensive experiments demonstrating its superiority over state-of-the-art methods in various challenging low-light scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2501_08038
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Low-Light Human Pose Estimation through Illumination-Texture Modulation
Zhang, Feng
Li, Ze
Zhu, Xiatian
Chen, Lei
Computer Vision and Pattern Recognition
As critical visual details become obscured, the low visibility and high ISO noise in extremely low-light images pose a significant challenge to human pose estimation. Current methods fail to provide high-quality representations due to reliance on pixel-level enhancements that compromise semantics and the inability to effectively handle extreme low-light conditions for robust feature learning. In this work, we propose a frequency-based framework for low-light human pose estimation, rooted in the "divide-and-conquer" principle. Instead of uniformly enhancing the entire image, our method focuses on task-relevant information. By applying dynamic illumination correction to the low-frequency components and low-rank denoising to the high-frequency components, we effectively enhance both the semantic and texture information essential for accurate pose estimation. As a result, this targeted enhancement method results in robust, high-quality representations, significantly improving pose estimation performance. Extensive experiments demonstrating its superiority over state-of-the-art methods in various challenging low-light scenarios.
title Robust Low-Light Human Pose Estimation through Illumination-Texture Modulation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.08038