E-3DPSM：用于基于事件的自我中心3D人体姿态估计的状态机
E-3DPSM: A State Machine for Event-based Egocentric 3D Human Pose Estimation
将连续时间状态机与事件流对齐，为事件相机下的单目3D人体姿态估计提供了一种实时、抗自遮挡和时序抖动的建模范式，可迁移到其他事件驱动的连续运动估计任务。
原文依据 E-3DPSM aligns continuous human motion with fine-grained event dynamics; it evolves latent states and predicts continuous changes in 3D joint positions associated with observed events
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论事件相机在基于头戴设备的单目自我中心3D人体姿态估计中具有多项优势，例如毫秒级时序分辨率、高动态范围和可忽略的运动模糊。现有方法有效利用了这些特性，但3D估计精度较低，在许多应用（例如沉浸式VR/AR）中不够充分。这是由于设计未完全针对事件流（例如其异步和连续的特性），导致对自遮挡和估计中的时序抖动高度敏感。本文重新思考该设定，并引入E-3DPSM，一种用于基于事件的自我中心3D人体姿态估计的事件驱动连续姿态状态机。E-3DPSM将连续人体运动与细粒度事件动态对齐；它演化潜变量状态并预测与观测事件相关的3D关节位置的连续变化，这些变化与直接的3D人体姿态预测融合，从而获得稳定且无漂移的最终3D姿态重建。E-3DPSM在单个工作站上以80 Hz实时运行，并在两个基准测试中取得新的最先进结果，精度提升高达19%（MPJPE），时序稳定性提升高达2.7倍。
英文原文摘要 1233 字符
Event cameras offer multiple advantages in monocular egocentric 3D human pose estimation from head-mounted devices, such as millisecond temporal resolution, high dynamic range, and negligible motion blur. Existing methods effectively leverage these properties, but suffer from low 3D estimation accuracy, insufficient in many applications (e.g., immersive VR/AR). This is due to the design not being fully tailored towards event streams (e.g., their asynchronous and continuous nature), leading to high sensitivity to self-occlusions and temporal jitter in the estimates. This paper rethinks the setting and introduces E-3DPSM, an event-driven continuous pose state machine for event-based egocentric 3D human pose estimation. E-3DPSM aligns continuous human motion with fine-grained event dynamics; it evolves latent states and predicts continuous changes in 3D joint positions associated with observed events, which are fused with direct 3D human pose predictions, leading to stable and drift-free final 3D pose reconstructions. E-3DPSM runs in real-time at 80 Hz on a single workstation and sets a new state of the art in experiments on two benchmarks, improving accuracy by up to 19% (MPJPE) and temporal stability by up to 2.7x.