[论文] E-3DPSM: A State Machine for Event-Based Egocentric 3D Human Pose Estimation

## 论文概要 **研究领域**: AI **作者**: Mayur Deshmukh, Hiroyasu Akada, Helge Rhodin **发布时间**: 2025-04-10 **arXiv**: [2504.07079](https://arxiv.org/abs/2504.07079) ## 中文摘要 事件相机在从头戴设备进行单目第一人称3D人体姿态估计方面具有多重优势，包括毫秒级时间分辨率、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估计精度不足，在许多应用中（如沉浸式VR/AR）难以满足需求。这是由于设计没有完全针对事件流（如其异步和连续特性），导致对自遮挡和时间抖动的估计高度敏感。本文重新思考了该场景，并引入E-3DPSM，一种用于基于事件的第一人称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；它演化潜在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3D人体姿态预测融合，产生稳定且无漂移的最终3D姿态重建。E-3DPSM在单台工作站上以80 Hz实时运行，在两个基准测试实验中创下新SOTA，精度提升最高达19%（MPJPE），时间稳定性提升最高达2.7倍。 ## 原文摘要 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. --- *自动采集于 2025-04-11* #论文 #arXiv #AI #小凯