# ByteDance-Seed/Depth-Anything-3

Depth Anything 3

Repository: https://github.com/ByteDance-Seed/Depth-Anything-3
Canonical: https://ross.abutalabs.com/products/depth-anything-3
Homepage: https://depth-anything-3.github.io/
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-07-27T06:07:26+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 35, longevity 21
- inputs: {"age_days": 294, "days_push": 37, "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 6213, forks 689 (observed 2026-08-28T04:09:40.064543+00:00)

## What it is
Depth Anything 3 (DA3) is a transformer-based model that predicts spatially consistent depth and geometry from any number of visual inputs, with or without known camera poses. It provides Python inference code and pretrained weights, including a streaming mode for ultra-long video sequences on modest GPU memory.

## Use cases
- estimate depth from a single image
- reconstruct 3D geometry from multiple views or video
- estimate camera poses from unposed images
- render novel views with 3D Gaussian splatting
- run depth inference on long videos with limited GPU memory
- build SLAM or visual-geometry pipelines on top of a pretrained model

## When to choose
- you need state-of-the-art monocular or multi-view depth estimation
- you need camera pose estimation and geometry from arbitrary unposed views
- you want a plain-transformer model trained only on public datasets
- you need streaming inference for long video under 12GB GPU memory

## When to avoid
- you need real-time depth on CPU or edge devices without a GPU
- you need metric depth with guaranteed absolute scale out of the box
- you need a lightweight model for production mobile deployment

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, computer-vision, image-processing, gpu-computing
- domain: computer-vision, deep-learning, machine-learning, artificial-intelligence, graphics
- platform: python, cross-platform
- tags: depth-estimation, monocular-depth, multi-view-geometry, camera-pose-estimation, 3d-reconstruction, transformer, novel-view-synthesis, slam, 3dgs, pytorch, gpu, linux

## Member repositories
- ByteDance-Seed/Depth-Anything-3 (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:40.064543+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 2026-08-29T17:47:16.461278+00:00, confidence not recorded.
  - readme: https://github.com/ByteDance-Seed/Depth-Anything-3 (fetched 2026-08-28T04:09:40.064543+00:00, sha 74dd4f6c1de1)
  - homepage: https://depth-anything-3.github.io/ (fetched 2026-08-29T08:43:36.986948+00:00, sha bdbd63981cc8)
  - registry_pypi: https://pypi.org/pypi/depth-anything-3/json (fetched 2026-08-29T08:43:36.996260+00:00, sha 465815314ee5)
- Data as of 2026-08-30T08:39:29.467469+00:00.