Description: BootsTAP: Bootstrapped Training for Tracking-Any-Point
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 demo
TAPIR is the foundational visual perception model for this work. It provides fast and accurate tracking of any point in a video, and has some cool video generation applications.
RoboTAP , ATM , and Track2Act demonstrate how TAP can transform few-shot learning in robotics.