基于移动多摄像机组的野外自-外视角3D手部跟踪
Ego-Exo 3D Hand Tracking in the Wild with a Mobile Multi-Camera Rig
AI总结：
针对自中心视觉手部3D跟踪数据集环境受限、泛化性差的问题，提出结合背部外相机与Meta Quest 3头显的无标记多相机系统及自-外跟踪流水线，可在野外环境下生成高精度3D手部标注，平衡真实感与标注精度。
摘要：
在无约束环境中精准实现手部及其与外界交互的3D跟踪，仍是自中心计算机视觉领域的一项重大挑战。除少数例外，现有数据集大多在受控实验室环境中采集，限制了环境多样性与模型泛化能力。为解决这一问题，我们提出一种新型无标记多相机系统，旨在采集精准的3D手部与物体数据，可在真实野外条件下实现近乎无约束的移动性。我们将搭载8台外中心相机的轻量化背部采集装置，与用户佩戴的Meta Quest 3头显（提供2个自中心视角）相结合。我们设计了一套自-外视角跟踪流水线，可基于该系统生成精准的3D手部姿态真值，并对其质量进行了严格评估。通过采集包含同步多视角图像与精准3D手部姿态的标注数据集，我们证明所提方法能够显著缓解环境真实感与3D标注精度之间的权衡问题。
英文摘要：
Accurate 3D tracking of hands and their interactions with the world in unconstrained settings remains a significant challenge for egocentric computer vision. With few exceptions, existing datasets are predominantly captured in controlled lab setups, limiting environmental diversity and model generalization. To address this, we introduce a novel marker-less multi-camera system designed to capture precise 3D hands and objects, which allows for nearly unconstrained mobility in genuinely in-the-wild conditions. We combine a lightweight, back-mounted capture rig with eight exocentric cameras, and a user-worn Meta Quest 3 headset, which contributes two egocentric views. We design an ego-exo tracking pipeline to generate accurate 3D hand pose ground truth from this system, and rigorously evaluate its quality. By collecting an annotated dataset featuring synchronized multi-view images and precise 3D hand poses, we demonstrate the capability of our approach to significantly reduce the trade-off between environmental realism and 3D annotation accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
