# sniklaus/3d-ken-burns

an implementation of 3D Ken Burns Effect from a Single Image using PyTorch

Repository: https://github.com/sniklaus/3d-ken-burns
Canonical: https://ross.abutalabs.com/products/3d-ken-burns
Language: Python
License: NOASSERTION
License Family: other
Topics: pytorch, python, cuda, deep-learning, cupy
Last push: 2026-06-01T16:29:31+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 85, release rhythm 35, longevity 100
- inputs: {"age_days": 2480, "days_push": 93, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1569, forks 222 (observed 2026-08-28T04:05:05.169937+00:00)

## What it is
A PyTorch reference implementation of the 3D Ken Burns Effect from a Single Image paper, which animates a still photo with a virtual camera scan and zoom subject to motion parallax. It includes automatic effect generation, a web interface for manually adjusting the camera path, and depth estimation tooling.

## Use cases
- turn a single photo into a 3D ken burns video
- animate a still image with parallax zoom
- estimate depth from a single image
- manually adjust a virtual camera path over a photo
- generate parallax video from photos

## When to choose
- you want to reproduce the 3D Ken Burns paper results
- you have a CUDA GPU and want automatic parallax animation from one image
- you need single-image depth estimation for view synthesis

## When to avoid
- you have no NVIDIA GPU or CUDA environment
- you need a maintained production tool rather than a research implementation
- you need commercial use of the dataset (CC BY-NC-SA licensed)

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, video-processing, computer-vision
- domain: computer-vision, deep-learning, media, image-processing
- platform: python, cross-platform
- tags: ken-burns-effect, depth-estimation, pytorch, cuda, cupy, video-generation, research-implementation, video, gpu, linux

## Member repositories
- sniklaus/3d-ken-burns (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:05.169937+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 2026-08-30T03:58:54.398750+00:00, confidence not recorded.
  - readme: https://github.com/sniklaus/3d-ken-burns (fetched 2026-08-28T04:05:05.169937+00:00, sha ce44f4eacd57)
- Data as of 2026-08-30T08:39:29.467469+00:00.