MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources
Authors:
- Baorui MaBMBaorui Ma
- Jiahui YangJYJiahui Yang
- Donglin DiDDDonglin Di
- Xuancheng ZhangXZXuancheng Zhang
- Jianxun CuiJCJianxun Cui
- Hao LiHLHao Li
- Yan XieYXYan Xie
- Wei ChenWCWei Chen
Preprint
Abstract
Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging due to heterogeneous sensor noise, camera-dependent biases, and metric ambiguity in noisy cross-source 3D data. We introduce Metric Anything, a simple and scalable pretraining framework that learns metric depth from noisy, diverse 3D sources without manually engineered prompts, camera-specific modeling, or task-specific architectures. Central to our approach is the Sparse Metric Prompt, created by randomly masking depth maps, which serves as a universal interface that decouples spatial reasoning from sensor and camera biases. Using about 20M image-depth pairs spanning reconstructed, captured, and rendered 3D data across 10000 camera models, we demonstrate-for the first time-a clear scaling trend in the metric depth track. The pretrained model excels at prompt-driven tasks such as depth completion, super-resolution and Radar-camera fusion, while its distilled prompt-free student achieves state-of-the-art results on monocular depth estimation, camera intrinsics recovery, single/multi-view metric 3D reconstruction, and VLA planning. We also show that using pretrained ViT of Metric Anything as a visual encoder significantly boosts Multimodal Large Language Model capabilities in spatial intelligence. These results show that metric depth estimation can benefit from the same scaling laws that drive modern foundation models, establishing a new path toward scalable and efficient real-world metric perception. We open-source MetricAnything at http://metric-anything.github.io/metric-anything-io/ to support community research.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces2025
- Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation2025
- FoundationStereo: Zero-Shot Stereo Matching2025
- OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations2024
- Depth Prompting for Sensor-Agnostic Depth Estimation2024
- Bilateral Propagation Network for Depth Completion2024
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data2024
- Adding Conditional Control to Text-to-Image Diffusion Models2023
- CompletionFormer: Depth Completion with Convolutions and Vision Transformers2023
- UASOL, a large-scale high-resolution outdoor stereo datasetScientific Data, 2019