Youran Ding

Matching Every Pair to Track Every Point: PairFormer for All-Pairs Tracking and Video Trajectory Fields

Tracking-any-point (TAP) answers query-conditioned correspondence but leaves the dense, all-pairs structure of a video implicit. We formulate All-Pairs Tracking (APT): given a video, predict dense displacement and visibility for every source-target frame pair, from which per-pixel trajectories can b