English

DELTAv2: Accelerating Dense 3D Tracking

Computer Vision and Pattern Recognition 2025-12-11 v2

Abstract

We propose a novel algorithm for accelerating dense long-term 3D point tracking in videos. Through analysis of existing state-of-the-art methods, we identify two major computational bottlenecks. First, transformer-based iterative tracking becomes expensive when handling a large number of trajectories. To address this, we introduce a coarse-to-fine strategy that begins tracking with a small subset of points and progressively expands the set of tracked trajectories. The newly added trajectories are initialized using a learnable interpolation module, which is trained end-to-end alongside the tracking network. Second, we propose an optimization that significantly reduces the cost of correlation feature computation, another key bottleneck in prior methods. Together, these improvements lead to a 5-100x speedup over existing approaches while maintaining state-of-the-art tracking accuracy.

Keywords

Cite

@article{arxiv.2508.01170,
  title  = {DELTAv2: Accelerating Dense 3D Tracking},
  author = {Tuan Duc Ngo and Ashkan Mirzaei and Guocheng Qian and Hanwen Liang and Chuang Gan and Evangelos Kalogerakis and Peter Wonka and Chaoyang Wang},
  journal= {arXiv preprint arXiv:2508.01170},
  year   = {2025}
}

Comments

Project page: https://snap-research.github.io/DELTAv2/

R2 v1 2026-07-01T04:30:31.521Z