Egocentric 3D hand pose estimation and gesture recognition are essential for immersive augmented/virtual reality, human-computer interaction, and robotics. However, conventional frame-based cameras suffer from motion blur and limited dynamic range, while existing event-based methods are hindered by ego-motion interference, monocular depth ambiguity, and the lack of large-scale real-world stereo datasets. To overcome these limitations, we propose EgoEV-HandPose, an end-to-end framework for joint 3D bimanual pose estimation and gesture recognition from stereo event streams. Central to our approach is KeypointBEV, a flexible stereo fusion module that lifts features into a canonical bird's-eye-view space and employs an iterative reprojection-guided refinement loop to progressively resolve depth uncertainty and enforce kinematic consistency. In addition, we introduce EgoEVHands, the first large-scale real-world stereo event-camera dataset for egocentric hand perception, containing 5,419 annotated sequences with dense 3D/2D keypoints across 38 gesture classes under varying illumination. Extensive experiments demonstrate that EgoEV-HandPose achieves state-of-the-art performance with an MPJPE of 30.54mm and 86.87% Top-1 gesture recognition accuracy, significantly outperforming RGB-based stereo and prior event-camera methods, particularly in low-light and bimanual occlusion scenarios, thereby setting a new benchmark for event-based egocentric perception. The established dataset and source code will be publicly released at https://github.com/ZJUWang01/EgoEV-HandPose.

翻译：自我中心三维手部姿态估计与手势识别对于沉浸式增强/虚拟现实、人机交互和机器人技术至关重要。然而，传统基于帧的相机受运动模糊和有限动态范围困扰，而现有基于事件的方法受到自我运动干扰、单目深度模糊以及缺乏大规模真实世界立体数据集的阻碍。为克服这些限制，我们提出了EgoEV-HandPose，一个用于从立体事件流中联合进行三维双手姿态估计与手势识别的端到端框架。我们方法的核心是KeypointBEV，一个灵活的立体融合模块，它将特征提升到规范的鸟瞰图空间，并采用迭代重投影引导的细化循环，逐步解决深度不确定性并强制执行运动学一致性。此外，我们引入了EgoEVHands，这是首个用于自我中心手部感知的大规模真实世界立体事件相机数据集，包含5,419个标注序列，涵盖38个手势类别下的密集三维/二维关键点，并具有不同的光照条件。大量实验表明，EgoEV-HandPose实现了最先进的性能，MPJPE达到30.54毫米，Top-1手势识别准确率达到86.87%，显著优于基于RGB的立体方法和先前的事件相机方法，特别是在低光和双手遮挡场景中，从而为基于事件的自我中心感知设立了新的基准。所建立的数据集和源代码将在https://github.com/ZJUWang01/EgoEV-HandPose 公开发布。