# microsoft/Bringing-Old-Photos-Back-to-Life

Bringing Old Photo Back to Life (CVPR 2020 oral)

Repository: https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life
Canonical: https://ross.abutalabs.com/products/bringing-old-photos-back-to-life
Homepage: https://arxiv.org/abs/2004.09484
Language: Python
License: MIT
License Family: permissive
Topics: image-restoration, old-photo-restoration, generative-adversarial-network, gans, pytorch, image-manipulation, photo-restoration, photos
Last push: 2023-10-26T08:06:57+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2261, "days_push": 1042, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 15704, forks 2096 (observed 2026-08-28T04:11:13.854977+00:00)

## What it is
The official PyTorch implementation of 'Bringing Old Photos Back to Life' (CVPR 2020 Oral), a deep learning model that restores old photos suffering from scratches, dust, noise, and blurriness using a triplet domain translation network with VAE latent spaces. It includes pretrained models, training code, and support for high-resolution inputs.

## Use cases
- restore old damaged family photos
- remove scratches and dust spots from scanned photographs
- fix noise and blurriness in degraded images
- enhance faces in old photos
- experiment with GAN-based image restoration research
- run photo restoration on a GPU with pretrained models

## When to choose
- you need to restore real old photos with mixed degradations like scratches, noise, and blur
- you want a research-grade reference implementation of the CVPR 2020 paper
- you have an Nvidia GPU and want pretrained models for photo restoration

## When to avoid
- you need a production-ready, optimized service with fast inference or easy deployment
- you lack a CUDA-capable GPU
- you need general-purpose modern photo enhancement rather than old-photo-specific restoration

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning, photography
- platform: python
- tags: image-restoration, gan, pytorch, old-photos, photo-enhancement, scratch-removal, face-enhancement, research-code, linux, gpu

## Member repositories
- microsoft/Bringing-Old-Photos-Back-to-Life (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:13.854977+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 2026-08-29T17:05:34.348885+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life (fetched 2026-08-28T04:11:13.854977+00:00, sha f1c820877ef3)
  - homepage: https://arxiv.org/abs/2004.09484 (fetched 2026-08-29T08:03:34.454039+00:00, sha fc3b3ed7294a)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T08:03:34.463076+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T08:03:34.466800+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T08:03:34.469273+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T08:03:34.464897+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.