English

RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classes

Computer Vision and Pattern Recognition 2026-04-07 v2

Abstract

Monocular Metric Depth Estimation (MMDE) is essential for physically intelligent systems, yet accurate depth estimation for underrepresented classes in complex scenes remains a persistent challenge. To address this, we propose RAD, a retrieval-augmented framework that approximates the benefits of multi-view stereo by utilizing retrieved neighbors as structural geometric proxies. Our method first employs an uncertainty-aware retrieval mechanism to identify low-confidence regions in the input and retrieve RGB-D context samples containing semantically similar content. We then process both the input and retrieved context via a dual-stream network and fuse them using a matched cross-attention module, which transfers geometric information only at reliable point correspondences. Evaluations on NYU Depth v2, KITTI, and Cityscapes demonstrate that RAD significantly outperforms state-of-the-art baselines on underrepresented classes, reducing relative absolute error by 29.2% on NYU Depth v2, 13.3% on KITTI, and 7.2% on Cityscapes, while maintaining competitive performance on standard in-domain benchmarks.

Keywords

Cite

@article{arxiv.2602.09532,
  title  = {RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classes},
  author = {Michael Baltaxe and Dan Levi and Sagie Benaim},
  journal= {arXiv preprint arXiv:2602.09532},
  year   = {2026}
}
R2 v1 2026-07-01T10:29:20.413Z