# YvanYin/Metric3D

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

Repository: https://github.com/YvanYin/Metric3D
Canonical: https://ross.abutalabs.com/products/metric3d
Homepage: https://jugghm.github.io/Metric3Dv2/
Language: Python
License: BSD-2-Clause
License Family: permissive
Topics: 3d-reconstruction, 3d-scenes, monocular-depth, monocular-depth-estimation, depth, depth-map, metric-depth-estimation, single-image-depth-prediction, zero-shot-transfer, zero-shot
Last push: 2025-03-13T07:25:00+00:00

## Health v2 (maintenance only)
Score: 33/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 11, release rhythm 35, longevity 81
- inputs: {"age_days": 1145, "days_push": 538, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2302, forks 171 (observed 2026-08-28T04:06:35.523819+00:00)

## What it is
Metric3D is the official PyTorch implementation of Metric3Dv1 and Metric3Dv2, monocular geometric foundation models that predict metric depth and surface normals from a single image with zero-shot transfer. It supports canonical camera space transformation, depth-normal joint estimation, and applications like 3D reconstruction and SLAM.

## Use cases
- estimate metric depth from a single image
- predict surface normals from photos
- zero-shot depth estimation on new scenes
- reconstruct 3D scenes from one image
- feed depth maps into SLAM pipelines
- benchmark monocular depth estimation on NYU and KITTI

## When to choose
- you need metric (absolute-scale) depth rather than relative depth from a single image
- you want state-of-the-art zero-shot depth and normal estimation
- you need a pretrained geometric foundation model for downstream 3D tasks

## When to avoid
- you need real-time depth on edge devices with limited compute
- you only need relative/monocular depth without metric scale
- you need multi-view or stereo depth estimation

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: monocular-depth-estimation, metric-depth, surface-normal-estimation, zero-shot, 3d-reconstruction, pytorch, foundation-model, single-image, gpu

## Member repositories
- YvanYin/Metric3D (main) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:35.523819+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:40:09.550681+00:00, confidence not recorded.
  - readme: https://github.com/YvanYin/Metric3D (fetched 2026-08-28T04:06:35.523819+00:00, sha b2b08b066d2c)
  - homepage: https://jugghm.github.io/Metric3Dv2/ (fetched 2026-08-29T10:20:18.116723+00:00, sha 2cb5997e174c)
- Data as of 2026-08-30T08:39:29.467469+00:00.