Metraipolis › archive › dc_87f259cec2e4

ReLift: Dense 3D Tracking as Lifted Trajectory Repair — arXiv:2610.42136

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.42136
License (as archived): CC0-1.0
Archived: 2026-11-02T08:03:37.146Z
SHA-256 of the archived text: 90ffd451e3607f894abf03322a8285d569156f37af872027029162cfc960c9c8
Stable URL of this page: https://metraipolis.com/documento/dc_87f259cec2e4

How to cite

ReLift: Dense 3D Tracking as Lifted Trajectory Repair — arXiv:2610.42136 — arXiv (en), https://arxiv.org/abs/2610.42136 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_87f259cec2e4 (Metraipolis archive dc_87f259cec2e4, sha256 90ffd451e3607f894abf03322a8285d569156f37af872027029162cfc960c9c8)

BibTeX

@misc{dc87f259cec2e4,
  title = {ReLift: Dense 3D Tracking as Lifted Trajectory Repair — arXiv:2610.42136},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42136},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_87f259cec2e4; sha256 90ffd451e3607f894abf03322a8285d569156f37af872027029162cfc960c9c8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42136. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 efficient feed-forward framework that recasts dense 3D tracking as geometric trajectory repair and completion. At its core, a trajectory corrector alternates attention along and across trajectories to preserve reliable observations, repair corrupted positions, and complete missing motion. Using only geometric inputs allows us to train directly on 3D trajectories with simulated lifting errors, decoupling training from images and from any specific tracker or geometry model. Concentrating 4D supervision on trajectory refinement yields a reusable model that consistently improves lifted trajectories across trackers and geometry providers without retraining, so it benefits directly from future advances in either component. On WorldTrack, ReLift achieves state-of-the-art mean accuracy, improving on the strongest baselines by 2.1 APD on all points and 3.0 on dynamic points, with faster configurations remaining competitive with leading 3D trackers while running faster than 4RC. Visit our supplementry page for more examples and code.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.42136 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-02T07:44:00.780Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).