Non-line-of-sight (NLOS) tracking has drawn increasing attention in recent years, due to its ability to detect object motion out of sight. Most previous works on NLOS tracking rely on active illumination, e.g., laser, and suffer from high cost and elaborate experimental conditions. Besides, these techniques are still far from practical application due to oversimplified settings. In contrast, we propose a purely passive method to track a person walking in an invisible room by only observing a relay wall, which is more in line with real application scenarios, e.g., security. To excavate imperceptible changes in videos of the relay wall, we introduce difference frames as an essential carrier of temporal-local motion messages. In addition, we propose PAC-Net, which consists of alternating propagation and calibration, making it capable of leveraging both dynamic and static messages on a frame-level granularity. To evaluate the proposed method, we build and publish the first dynamic passive NLOS tracking dataset, NLOS-Track, which fills the vacuum of realistic NLOS datasets. NLOS-Track contains thousands of NLOS video clips and corresponding trajectories. Both real-shot and synthetic data are included. Our codes and dataset are available at https://againstentropy.github.io/NLOS-Track/.

翻译：非视距（NLOS）跟踪因能检测视线外的物体运动而近年来备受关注。以往多数NLOS跟踪工作依赖主动照明（如激光），存在成本高、实验条件苛刻等问题。此外，受限于过度简化的实验设置，这些技术距离实际应用仍有较大差距。相比之下，我们提出了一种纯被动方法，仅通过观察反射墙面即可追踪不可见房间内行走的人，这更符合真实应用场景（如安防）。为挖掘反射墙视频中难以察觉的变化，我们引入差分帧作为时间局部运动信息的关键载体。此外，我们提出PAC-Net，该网络由交替传播与校正模块构成，能有效利用帧级粒度上的动态和静态信息。为评估所提方法，我们构建并发布了首个动态被动NLOS跟踪数据集NLOS-Track，填补了真实场景NLOS数据集的空白。该数据集包含数千个NLOS视频片段及对应轨迹，涵盖实拍与合成数据。我们的代码和数据集已开源在https://againstentropy.github.io/NLOS-Track/。