# DepthAnything/Video-Depth-Anything

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Repository: https://github.com/DepthAnything/Video-Depth-Anything
Canonical: https://ross.abutalabs.com/products/video-depth-anything
Homepage: https://videodepthanything.github.io/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: depth-estimation, video-depth, monocular-depth-estimation, transformer
Last push: 2025-10-07T06:00:12+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 45, release rhythm 35, longevity 42
- inputs: {"age_days": 589, "days_push": 330, "days_rel": 352, "gap_med": 62.0, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2087, forks 193 (observed 2026-08-28T04:06:11.999189+00:00)

## What it is
Video Depth Anything is a transformer-based monocular depth estimation model for arbitrarily long videos, built on Depth Anything V2. It provides temporally consistent relative and metric depth with faster inference and fewer parameters than diffusion-based alternatives.

## Use cases
- estimate depth maps from long videos
- generate temporally consistent video depth
- recover metric depth from monocular video
- unproject video frames to point clouds
- stream depth estimation for long videos
- benchmark video depth models

## When to choose
- you need consistent depth for super-long videos
- you want faster, lighter inference than diffusion-based depth models
- you need both relative and metric depth options

## When to avoid
- you only need single-image depth without temporal consistency
- you need real-time depth on CPU without a GPU

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, computer-vision, video-processing, image-processing
- domain: computer-vision, machine-learning, artificial-intelligence
- platform: python
- tags: depth-estimation, monocular-depth, video-depth, transformer, metric-depth, streaming-inference, cvpr-2025, video, gpu

## Member repositories
- DepthAnything/Video-Depth-Anything (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:11.999189+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 2026-08-30T02:55:43.659647+00:00, confidence not recorded.
  - readme: https://github.com/DepthAnything/Video-Depth-Anything (fetched 2026-08-28T04:06:11.999189+00:00, sha 8c47608cc67d)
  - homepage: https://videodepthanything.github.io/ (fetched 2026-08-29T10:35:33.620482+00:00, sha bfdadb93cde3)
- Data as of 2026-08-30T08:39:29.467469+00:00.