We present SpatialTrackerV2, a feed-forward 3D point tracking method for monocular videos. Going beyond modular pipelines built on off-the-shelf components for 3D tracking, our approach unifies the intrinsic connections between point tracking, monocular depth, and camera pose estimation into a high-performing and feedforward 3D point tracker. It decomposes world-space 3D motion into scene geometry, camera ego-motion, and pixel-wise object motion, with a fully differentiable and end-to-end architecture, allowing scalable training across a wide range of datasets, including synthetic sequences, posed RGB-D videos, and unlabeled in-the-wild footage. By learning geometry and motion jointly from such heterogeneous data, SpatialTrackerV2 outperforms existing 3D tracking methods by 30%, and matches the accuracy of leading dynamic 3D reconstruction approaches while running 50× faster.
@article{arxiv.2507.12462,
title = {SpatialTrackerV2: 3D Point Tracking Made Easy},
author = {Yuxi Xiao and Jianyuan Wang and Nan Xue and Nikita Karaev and Yuri Makarov and Bingyi Kang and Xing Zhu and Hujun Bao and Yujun Shen and Xiaowei Zhou},
journal= {arXiv preprint arXiv:2507.12462},
year = {2025}
}
Comments
International Conference on Computer Vision, ICCV 2025. Huggingface Demo: https://huggingface.co/spaces/Yuxihenry/SpatialTrackerV2, Code: https://github.com/henry123-boy/SpaTrackerV2