# aim-uofa/AdelaiDepth

This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.

Repository: https://github.com/aim-uofa/AdelaiDepth
Canonical: https://ross.abutalabs.com/products/adelaidepth
Language: Python
License: CC0-1.0
License Family: permissive
Topics: 3d-scene-shape, depth-prediction
Last push: 2023-11-10T08:14:10+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2113, "days_push": 1027, "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 1106, forks 148 (observed 2026-08-28T04:03:36.506237+00:00)

## What it is
AdelaiDepth is an open-source toolbox for monocular depth prediction and 3D scene reconstruction from single images, containing research projects like 3D Scene Shape (LeReS), DiverseDepth, and Virtual Normal. It provides pretrained models, training code, and datasets from academic computer vision research.

## Use cases
- estimate depth from a single image
- reconstruct 3D scene shape from one photo
- generate point clouds from monocular images
- train a depth prediction model
- compare monocular depth estimation algorithms
- run depth estimation on gpu

## When to choose
- you need state-of-the-art monocular depth estimation with pretrained models
- you want to reproduce or build on published depth estimation research
- you need 3D scene reconstruction from a single RGB image

## When to avoid
- you need real-time depth estimation on edge devices
- you want a production-ready maintained product with active support
- you need stereo or multi-view depth estimation rather than monocular

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, graphics
- platform: python
- tags: monocular-depth-estimation, 3d-reconstruction, depth-prediction, point-cloud, research-code, pytorch, linux, gpu

## Member repositories
- aim-uofa/AdelaiDepth (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:36.506237+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 2026-08-30T06:44:13.228141+00:00, confidence not recorded.
  - readme: https://github.com/aim-uofa/AdelaiDepth (fetched 2026-08-28T04:03:36.506237+00:00, sha 6221504e32e1)
- Data as of 2026-08-30T08:39:29.467469+00:00.