Dense 3D tracking from monocular video requires establishing point correspondences over time, estimating their depth, and inferring their trajectories during occlusion. Existing methods typically lear
ReLift improves dense 3D tracking by repairing and completing lifted trajectories using geometric trajectory refinement without requiring image-based training.
Dense 3D tracking from monocular video requires establishing point correspondences over time, estimating their depth, and inferring their trajectories during occlusion. Existing methods typically learn these tasks jointly, a demanding objective given the scarcity of 4D supervision. We show that strong pretrained 2D trackers and 3D geometry models provide an effective foundation: lifted trajectories, with occluded segments simply interpolated, already rival dedicated 3D trackers using the same geometry. However, lifted trajectories inherit correspondence and depth errors, and under occlusion, their depth comes from the occluder rather than the tracked point. We introduce ReLift, an…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
ReLift: Dense 3D Tracking as Lifted Trajectory Repair was first seen on Hugging Face · Daily papers on Nov 2, 2026. Since then it has appeared in 13 checks on 2 different days. Its best position was #11 of 30, reached on Nov 3, 07:28 UTC. It dropped off the list after Nov 3, 09:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 3, 09:28 UTC, after 2 days of trending.
#11 on Hugging Face · Daily papers, on Nov 3, 07:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 2, 2026 and has been on the list on 2 days (13 checks) since.