No AI summary available for this article.
Why It Matters
Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over long horizons, or track all points across only short clips.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over long horizons, or track all points across only short clips. We introduce TrackEverything, a 3D point tracker that breaks this trade-off by representing videos as persistent 3D scene tracks in world coordinates. Grounded in the insight that videos are 2D projections of an underlying 3D world, TrackEverything decouples model complexity from video duration, allowing it to scale with unique physical scene geometry instead. Our approach introduces three key innovations. First, we empl...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.30222v1 · Indexed about 1 hour ago