用连续流模型提升人体姿态估计的不确定性感知能力
Continuous Normalizing Flows for Uncertainty-Aware Human Pose Estimation
- 将连续归一化流融入回归模型，实现动态分布建模
- 在2D/3D姿态估计上同时提升精度与不确定性量化效果
- 兼顾高精度与计算效率，适合对可靠性要求高的应用
人体姿态估计在虚拟现实和动作分析中日益重要，但现有方法难以兼顾精度、计算效率与可靠的不确定性量化（UQ）。传统回归方法假设输出分布固定，导致不确定性估计不佳；热图方法虽能有效建模分布，但资源消耗大。为此，本文提出连续流残差估计（CFRE），将连续归一化流（CNFs）集成到回归模型中，实现输出分布的动态适应。大量实验表明，CFRE在保持计算效率的同时，在2D与3D人体姿态估计任务上均实现了更高的精度与更可靠的不确定性量化。
原文摘要 · Abstract (English)
Human Pose Estimation (HPE) is increasingly important for applications like virtual reality and motion analysis, yet current methods struggle with balancing accuracy, computational efficiency, and reliable uncertainty quantification (UQ). Traditional regression-based methods assume fixed distributions, which might lead to poor UQ. Heatmap-based methods effectively model the output distribution using likelihood heatmaps, however, they demand significant resources. To address this, we propose Continuous Flow Residual Estimation (CFRE), an integration of Continuous Normalizing Flows (CNFs) into regression-based models, which allows for dynamic distribution adaptation. Through extensive experiments, we show that CFRE leads to better accuracy and uncertainty quantification with retained computational efficiency on both 2D and 3D human pose estimation tasks.
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。