# hukkelas/DeepPrivacy

DeepPrivacy: A Generative Adversarial Network for Face Anonymization

Repository: https://github.com/hukkelas/DeepPrivacy
Canonical: https://ross.abutalabs.com/products/deepprivacy
Language: Python
License: MIT
License Family: permissive
Last push: 2023-11-19T15:56:56+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": 2556, "days_push": 1018, "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 1316, forks 170 (observed 2026-08-28T04:04:20.717815+00:00)

## What it is
DeepPrivacy is a PyTorch-based GAN that automatically anonymizes faces in images and videos by generating realistic synthetic replacements. It detects faces with DSFD and uses sparse pose information to guide anonymization, and is superseded by DeepPrivacy2.

## Use cases
- anonymize faces in photos for gdpr compliance
- blur or replace faces in video footage
- generate synthetic faces to replace real ones in datasets
- anonymize images before publishing them
- redact faces from surveillance or street photography
- run face anonymization on a webcam stream

## When to choose
- you need fully automatic, realistic face anonymization in images or videos
- you want a research-grade GAN anonymization pipeline with a CLI
- you need privacy-preserving imagery without manual editing

## When to avoid
- you want the best anonymization quality - use DeepPrivacy2 instead
- you need anonymization of full bodies or other objects, not just faces
- you have no GPU and need fast real-time processing

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning, computer-vision, privacy
- domain: computer-vision, image-processing, privacy, deep-learning
- platform: python, windows
- tags: gan, face-anonymization, face-detection, image-inpainting, pytorch, gdpr, video-anonymization, linux, macos, docker, gpu

## Member repositories
- hukkelas/DeepPrivacy (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:20.717815+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 2026-08-30T04:48:29.139771+00:00, confidence not recorded.
  - readme: https://github.com/hukkelas/DeepPrivacy (fetched 2026-08-28T04:04:20.717815+00:00, sha 0afcb95ec128)
- Data as of 2026-08-30T08:39:29.467469+00:00.