AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend

Hengyi Wang, Lourdes Agapito

Abstract

We present AMB3R, a multi-view feed-forward model for dense 3D reconstruction on a metric-scale that addresses diverse 3D vision tasks. The key idea is to leverage a sparse, yet compact, volumetric scene representation as our backend, enabling geometric reasoning with spatial compactness. Although trained solely for multi-view reconstruction, we demonstrate that AMB3R can be seamlessly extended to uncalibrated visual odometry (online) or large-scale structure from motion without the need for task-specific fine-tuning or test-time optimization. Compared to prior pointmap-based models, our approach achieves state-of-the-art performance in camera pose, depth, and metric-scale estimation, 3D reconstruction, and even surpasses optimization-based SLAM and SfM methods with dense reconstruction priors on common benchmarks.
BibTeX
@inproceedings{wang2026amb,
  author = {Hengyi Wang and Lourdes Agapito},
  title = {{AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2026},
  url = {https://openreview.net/forum?id=DSafzLwL67},
}
Figure