cs.CVNov 5, 2026

MetricTrail: Revisiting the Power of Metric Depth and Local Optimization for Long-Sequence Streaming 3D Reconstruction

Authors: Jingnan Gao, Jiahui Huang, Sven Elflein, Jianhao Zheng, Bingxin Ke, Xiaokang Yang, Yichao Yan, Laura Leal-Taixé, 

Organizations: NVIDIA · Shanghai Jiao Tong University · University of Toronto, Vector Institute · Stanford University

Abstract

We present MetricTrail, a streaming system for accurate camera motion estimation and dense reconstruction from long monocular videos. To keep inference efficient over long sequences, we revisit DPVO's sparse local estimator. We find that single-image metric depth substantially improves its trajectory accuracy, without retraining the correspondence network or enlarging the optimization window. Metric predictions initialize patch depths and remain as soft constraints during optimization. We further improve correspondence estimation through learned adapters that augment matching features and recurrent context with frozen DINOv3 representations. The correspondence estimator and adapters are trained on diverse short clips without additional long-sequence training. This modular design also allows the depth provider to be independently upgraded and supports supplied camera intrinsics and calibrated stereo observations without retraining. Under the reported RGB-only protocols, MetricTrail achieves the lowest average trajectory error among evaluated methods on KITTI, Oxford Spires, and VBR. Pairing the estimated poses with single-image depth predictions also produces strong dense reconstruction on indoor and outdoor benchmarks and coherent reconstructions of in-the-wild videos. With supplied intrinsics, the system processes KITTI-02 at 12.70 FPS with 3.21 GB peak GPU memory.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. PAS3R: Pose-Adaptive Streaming 3D Reconstruction for Long Video Sequences

    Mar 22, 2026Lanbo Xu, Liang Guo, Caigui Jiang +1Streaming 3D ReconstructionMonocular 3D Reconstruction

  2. LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos

    May 17, 2026Chenyi Xu, Yihao Wu, Liqi Yan +43D Point Tracking4D Reconstruction