Accurate and generalizable metric depth estimation is crucial for various computer vision applications but remains challenging due to the diverse depth scales encountered in indoor and outdoor environments. In this paper, we introduce Metric-Solver, a novel sliding anchor-based metric depth estimation method that dynamically adapts to varying scene scales.
Our approach leverages an anchor-based representation, where a reference depth serves as an anchor to separate and normalize the scene depth into two components: scaled near-field depth and tapered far-field depth. The anchor acts as a normalization factor, enabling the near-field depth to be normalized within a consistent range while mapping far-field depth smoothly toward zero. Through this approach, any depth from zero to infinity in the scene can be represented within a unified representation, effectively eliminating the need to manually account for scene scale variations.
More importantly, for the same scene, the anchor can slide along the depth axis, dynamically adjusting to different depth scales. A smaller anchor provides higher resolution in the near-field, improving depth precision for closer objects while a larger anchor improves depth estimation in far regions. This adaptability enables the model to handle depth predictions at varying distances and ensure strong generalization across datasets. Our design enables a unified and adaptive depth representation across diverse environments. Extensive experiments demonstrate that Metric-Solver outperforms existing methods in both accuracy and cross-dataset generalization.
Given an input image, we first employ a large-scale image encoder to extract latent features, as illustrated in (a). Next, these latent features, combined with the sampled anchor depth from the anchor pool, as shown in (b), are fed into a two-branch decoder. Here, the anchor represents a boundary between near and far, and is divided at the pixel level through the anchor mask \( m_{sm} \). During training, all different anchors have a chance to be randomly selected from the pool. Then the two-branch decoder predicts near-depth \( d_{sn} \), anchor mask \( m_{sm} \), and far-depth \( d_{tf} \), as depicted in (c). Finally, the two depth representations are fused using the mask to generate the final complete depth prediction, as demonstrated in (d).
With Metric-Solver, depth estimation can be performed from a single monocular image, enabling monocular reconstruction of the environment.
Metric-Solver supports metric depth estimation from video sequences, thereby facilitating the reconstruction of dynamic 4D environments.
@article{wen2025metricsolver
author = {Wen,Tao and Wang,Jiepeng and Chen,Yabo and Xu,Shugong and Zhang,Chi and Li,Xuelong},
title = {Metric-Solver: Sliding Anchored Metric Depth Estimation from a Single Image},
journal = {arXiv preprint arXiv:2504.12103},
year = {2025},
}