Previous feed-forward 4D reconstruction methods either predict per-frame static point clouds, ignoring foreground motion, or estimate point cloud trajectories while being limited to small camera motions. This restricts their ability to aggregate observations over time and reconstruct complete dynamic scenes under large viewpoint changes. To address this limitation, we propose OmniX, a feed-forward 4D reconstruction framework that predicts dense 3D point trajectories for every pixel from videos with large camera motion. OmniX decouples dynamic motion modeling from static geometry prediction and represents motion using a compact set of dynamic tokens. By leveraging the sparse and low-rank structure of 3D motion, these tokens generate trajectory fields for all pixels across all images while efficiently preserving global interactions. To facilitate training, we further build an automatic UE5-based 4D data engine and introduce a large-scale dataset containing 80K scenes and 1.28M multi-view videos with full geometric annotations. OmniX achieves state-of-the-art performance on dense 3D point trajectory prediction and 3D point tracking, while also demonstrating competitive results on video depth estimation and camera pose estimation.
If the embedded video does not load, please watch it directly on YouTube.
This project builds upon several excellent open-source projects and research efforts. We sincerely thank the authors and contributors of CUT3R, Depth Anything 3, VGGT, and WorldMirror for their inspiring works, released models, codebases, and resources.
If you find this work useful, please consider citing:
@inproceedings{jiang2026omnix,
title = {OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields},
author = {Jiang, Yanqin and Wang, Tengfei and Wang, Zhengwei and Cao, Chenjie and Wu, Junta and Luo, Wenhan and Hu, Weiming and Gao, Jin and Guo, Chunchao},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2026}
}