cs.CVOct 30, 2026

ReLift: Dense 3D Tracking as Lifted Trajectory Repair

Authors: Assaf Singer, Maroun Khriesh, Noam Rotstein, Yoni Kasten, Or Litany

Organizations: Technion – Israel Institute of Technology · NVIDIA

Abstract

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.

Figures & tables

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking

    May 12, 2026Jisu Nam, Jahyeok Koo, Soowon Son +4Point Tracking3D Point Tracking

  2. Track4D: Representing Dense 3D Tracking for Video Diffusion Models

    Nov 11, 2026Yushi Lan, Zeren Jiang, Kelvin Li +33D Point TrackingVideo Diffusion Models

  3. MoSE3: Learning World-Space SE(3) at Every Pixel

    Oct 2, 2026Jiahuan Cheng, Zhiyi Li, Tian Xia +33D Point Tracking