vufinder/depth-anything-v3-metric

Monocular metric depth estimation

Public
10.7K runs
@article{depthanything3,
  title={Depth Anything 3: Recovering the visual space from any views},
  author={Haotong Lin and Sili Chen and Jun Hao Liew and Donny Y. Chen and Zhenyu Li and Guang Shi and Jiashi Feng and Bingyi Kang},
  journal={arXiv preprint arXiv:2511.10647},
  year={2025}
}

Note: to obtain final metric depth, the results need to be scaled according to following formula: metric_depth = focal_lenght * depth / 300, where the focal length should be given in pixels.

Model created
Model updated