LAMP：度量三维世界中的定位感知多相机人体跟踪
LAMP: Localization Aware Multi-camera People Tracking in Metric 3D World
「先提升后拟合」的思路值得借鉴：先用已知的 6-DoF 位姿与标定把各相机 2D 关键点提升到统一世界坐标系，形成时空射线云，再用端到端 Transformer 直接拟合 3D 人体运动；这样就把观察者自身运动与目标运动解耦，可复用于任何带位姿的多相机或动态相机人体捕捉场景。
原文依据 convert detected 2D body keypoints from all cameras over a temporal window into a unified 3D world reference frame
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从第一视角多相机设备中跟踪三维人体运动，面临严重的自运动以及部分可见或遮挡的挑战。现有方法面向由静态或缓慢移动相机拍摄的单目视频设计，难以利用多视角、已标定且已定位的输入，因而在动态第一视角拍摄中表现脆弱、容易失败。我们提出 LAMP（定位感知多相机人体跟踪）：一个新颖而简洁的框架，通过早期解耦观察者运动与目标运动来解决该问题。LAMP 引入两步流程：首先，利用设备已知的 6-DoF 位姿与标定，将时序窗口内所有相机检测到的 2D 人体关键点转换到统一的三维世界参考系中；其次，一个端到端训练的 Transformer 模型直接在世界坐标下对这一时空射线云拟合三维人体运动。这种「先提升后拟合」的方式能够学习并利用世界空间中人体运动的自然先验，同时提供一个优雅的框架，灵活融合来自多个时间上异步、部分观测且处于运动中的相机的信息。LAMP 在单目基准上取得最优结果，并在我们所针对的第一视角多相机设定下显著优于基线方法。
英文原文摘要 1322 字符
Tracking 3D human motion from egocentric, multi-camera devices is challenged by severe egomotion and partial visibility or occlusions. Existing methods are designed for monocular video often recorded from static or slowly-moving cameras and cannot easily leverage multi-view, calibrated and localized input. This makes them brittle and prone to fail on dynamic egocentric captures. We propose LAMP (Localization Aware Multi-camera People Tracking): a novel, simple framework to solve this via early disentanglement of observer and target motion. LAMP introduces a two-step process: First, we leverage the device's known 6-DoF pose and calibration to convert detected 2D body keypoints from all cameras over a temporal window into a unified 3D world reference frame. Second, an end-to-end-trained Transformer model fits 3D human motion directly to this spatio-temporal ray cloud in world coordinates. This "lift-then-fit" approach allows to learn and leverage a natural prior over world-space human motion, as well as providing an elegant framework to flexibly incorporate information from multiple, temporally asynchronous, partially observing, and moving cameras. LAMP achieves state-of-the-art results on monocular benchmarks, while significantly outperforming baselines for our targeted egocentric multi-camera setting.