UST-Hand：面向3D自监督手部姿态估计的不确定性感知时空点云交互网络
UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimation
用条件归一化流建模手部姿态分布并采样多假设，再把多假设映射到统一概率点云空间做多视角与时序特征交互，这一「不确定性采样+点云时空融合」的范式可直接迁移到其他缺乏标注的人体/物体关键点与姿态自监督任务。
原文依据 UST-Hand employs a conditional normalizing flow model to capture hand pose distributions and samples diverse hypotheses
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论人工标注精确的3D手部姿态极其耗时且耗费人力。现有的自监督手部姿态估计方法利用输入图像与渲染输出之间的差异，或多视角一致性约束，作为优化网络的驱动力，并逐步提升姿态精度。然而，这些方法极易受到噪声伪标签的影响，且忽视了充分利用细粒度空间相关性的重要性，从而削弱了模型训练的稳定性。为解决这些问题，我们提出UST-Hand，一个自监督学习框架，它估计手部姿态的不确定性分布并构建概率点云特征空间，从而支持复杂的时空关系建模。UST-Hand采用条件归一化流模型来捕捉手部姿态分布并采样多样化的假设，在噪声伪标签监督下实现鲁棒学习并增强稳定性。这些多假设被映射到统一的概率3D点云空间，以进行多视角与时序特征交互，全面探索手部运动模式与细粒度空间相关性。在三个具有挑战性的数据集上的大量实验表明，UST-Hand达到了最优性能，在平均每顶点位置误差（MPVPE）上比现有自监督方法最高提升37.8%。
英文原文摘要 1446 字符
Manually annotating accurate 3D hand poses is extremely time-consuming and labor-intensive. Existing self-supervised hand pose estimation methods leverage the discrepancy between input images and rendered outputs, or multi-view consistency constraints, as the driving force to optimize networks and progressively refine pose accuracy. However, these methods are highly susceptible to noisy pseudo-labels and overlook the importance of fully exploiting fine-grained spatial correlations, which undermines the stability of model training. To address these issues, we propose UST-Hand, a self-supervised learning framework that estimates uncertainty distribution of hand pose and constructs a probabilistic point cloud feature space, which enables the complex spatiotemporal relationship modeling. UST-Hand employs a conditional normalizing flow model to capture hand pose distributions and samples diverse hypotheses, facilitating robust learning under noisy pseudo-labels supervision with enhanced stability. These multi-hypothesis are mapped to a unified probabilistic 3D point cloud space for multi-view and temporal feature interaction, comprehensively exploring hand motion patterns and fine-grained spatial correlations. Extensive experiments on three challenging datasets demonstrate that UST-Hand achieves state-of-the-art performance, outperforming existing self-supervised methods by up to 37.8% in Mean Per Vertex Position Error (MPVPE).