通过分频处理提升极暗环境下的姿态估计精度
Robust Low-Light Human Pose Estimation through Illumination-Texture Modulation
- 分频处理：低频补光、高频去噪，针对性增强关键信息
- 在极端低光下实现更高姿态估计准确率，超越现有方法
- 适合夜视监控、自动驾驶等弱光场景应用
极低光照下图像亮度不足且高ISO噪声严重，导致视觉细节模糊，给人体姿态估计带来巨大挑战。现有方法依赖像素级增强，易损失语义信息，难以在极端低光条件下实现鲁棒特征学习。本文提出基于频率的低光人体姿态估计框架，遵循‘分而治之’原则：不统一增强整图，而是对低频成分动态补光，对高频成分进行低秩去噪，有效增强语义与纹理信息，从而获得更鲁棒、高质量的表征。大量实验表明，在多种严苛低光场景中，该方法显著优于当前最优方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。