RAM：在野外恢复任意三维人体运动
RAM: Recover Any 3D Human Motion in-the-Wild
RAM 将运动感知语义跟踪器与自适应卡尔曼滤波结合，在严重遮挡下实现鲁棒的身份关联，并利用记忆增强的时序 HMR 模块注入时空先验，为野外多人 3D 人体运动捕捉提供了可复用的实时框架。
原文依据 RAM incorporates a motion-aware semantic tracker with adaptive Kalman filtering to achieve robust identity association under severe occlusions
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单目视频中恢复野外三维人体运动仍然具有挑战性，原因在于遮挡、快速运动和视角变化。为应对这些挑战，我们提出了 Recover-Anyone 模块（RAM），一个用于实时且准确的三维人体运动重建的统一框架。RAM 结合了运动感知语义跟踪器与自适应卡尔曼滤波，以在严重遮挡和动态交互下实现鲁棒的身份关联。记忆增强的时序 HMR 模块通过注入时空先验来进一步增强人体运动重建，实现一致且平滑的运动估计。此外，一个轻量级预测器模块预测未来姿态以保持重建连续性，而门控组合器自适应地融合重建特征和预测特征以确保连贯性和鲁棒性。在 PoseTrack 和 3DPW 等野外多人基准上的实验表明，RAM 在零样本跟踪稳定性和三维精度上均显著优于之前的最优方法，为野外无标记三维人体运动捕捉提供了一个可泛化的范式。
英文原文摘要 1138 字符
Recovering 3D human motion from monocular videos in-the-wild remains challenging due to occlusions, rapid movements, and viewpoint variations. To address these challenges, we introduce **Recover-Anyone Module (RAM)**, a unified framework for real-time and accurate 3D human motion reconstruction. RAM incorporates a motion-aware semantic tracker with adaptive Kalman filtering to achieve robust identity association under severe occlusions and dynamic interactions. A memory-augmented Temporal HMR module further enhances human motion reconstruction by injecting spatio-temporal priors for consistent and smooth motion estimation. Moreover, a lightweight Predictor module forecasts future poses to maintain reconstruction continuity, while a gated combiner adaptively fuses reconstructed and predicted features to ensure coherence and robustness. Experiments on in-the-wild multi-person benchmarks such as PoseTrack and 3DPW, demonstrate that RAM substantially outperforms previous state-of-the-art in both Zero-shot tracking stability and 3D accuracy, offering a generalizable paradigm for markerless 3D human motion capture in-the-wild.