NTH

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

AuthorsJingnan Gao, Jiahui Huang, Sven Elflein, Jianhao Zheng, Bingxin Ke, Xiaokang Yang, Yichao Yan, Laura Leal-Taixé, Qunjie Zhou, Jiawei Ren, Shengyu Huang

AffiliationsNVIDIA · Shanghai Jiao Tong University · University of Toronto, Vector Institute · Stanford University · Equal advising https://research.nvidia.com/labs/sil/projects/metrictrail/

November 13, 2026 2 min read
Watch on YouTube
The one-line take

MetricTrail uses metric depth and DINOv3 features to make streaming 3D reconstruction from long videos more accurate and efficient.

Key results

1.77
Oxford Spires average ATE

Meters; full-sequence trajectory error.

65.6%
Oxford Spires ATE reduction

Reduction relative to LingBot-MAP, whose average ATE is 5.15 m.

10.88
VBR average ATE with loop closure

Meters; full-sequence trajectory error.

0.04
7Scenes Chamfer distance

Meters; dense reconstruction.

12.70
KITTI-02 throughput

FPS with supplied intrinsics on an NVIDIA A100.

3.21
KITTI-02 peak GPU memory

GB with supplied intrinsics.

What the paper found

MetricTrail from NVIDIA strengthens DPVO’s bounded local optimization for long-video 3D reconstruction without widening its optimization window. It initializes sparse patch depths with MoGe-2 metric predictions and keeps them as robust soft constraints during bundle adjustment, anchoring scale while allowing multi-view evidence to correct unreliable depths. Frozen DINOv3-S/16 features, fused through learned adapters, improve patch matching and recurrent context; adaptation uses short clips rather than long-sequence training. On Oxford Spires, MetricTrail reaches 1.77 m average trajectory error, 65.6% lower than LingBot-MAP’s 5.15 m. With loop closure, its VBR trajectory error is 10.88 m. Dense reconstruction records 0.04 m Chamfer distance on 7Scenes. With supplied intrinsics on KITTI-02, the system runs at 12.70 FPS with 3.21 GB peak GPU memory on an NVIDIA A100. It also supports calibrated stereo and independently replaceable depth providers.

Original 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.

Read the original paper

More in Computer Vision

Browse all 82 papers →