To endow models with greater understanding of physics and motion, it is
useful to enable them to perceive how solid surfaces move and deform in real
scenes. This can be formalized as Tracking-Any-Point (TAP), which requires the
algorithm to be able to track any point corresponding to a solid surface in a
video, potentially densely in space and time. Large-scale ground-truth training
data for TAP is only available in simulation, which currently has limited
variety of objects and motion. In this work, we demonstrate how large-scale,
unlabeled, uncurated real-world data can improve a TAP model with minimal
architectural changes, using a self-supervised student-teacher setup. We
demonstrate state-of-the-art performance on the TAP-Vid benchmark surpassing
previous results by a wide margin: for example, TAP-Vid-DAVIS performance
improves from 61.3% to 66.4%, and TAP-Vid-Kinetics from 57.2% to 61.5%.

通过自我监督的师生设置，使用大规模无标签、无筛选的真实世界数据，以最小的架构改变改进 Tracking-Any-Point (TAP) 模型，实现了在 TAP-Vid 基准测试中的最新性能，超过先前研究结果很大幅度：例如、TAP-Vid-DAVIS 性能从 61.3% 提高到 66.4%，TAP-Vid-Kinetics 从 57.2% 提高到 61.5%。