# richzhang/colorization

Automatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.

Repository: https://github.com/richzhang/colorization
Canonical: https://ross.abutalabs.com/products/colorization
Homepage: http://richzhang.github.io/colorization/
Language: Python
License: BSD-2-Clause
License Family: permissive
Topics: caffe, colorization, automatic-colorization, deep-learning, deep-learning-algorithms, computer-vision
Last push: 2023-11-27T04:46:28+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3813, "days_push": 1010, "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 3461, forks 922 (observed 2026-08-28T04:08:05.669336+00:00)

## What it is
A Python library implementing automatic colorization of grayscale photos using deep neural networks from the ECCV 2016 'Colorful Image Colorization' paper and the SIGGRAPH 2017 follow-up. It provides pretrained PyTorch models (eccv16 and siggraph17) plus a demo script for colorizing images.

## Use cases
- colorize black and white photos automatically
- add plausible colors to grayscale images with a pretrained model
- load a colorization model in Python for image restoration
- restore old family photographs with deep learning
- compare ECCV16 and SIGGRAPH17 colorization models
- batch colorize historical photo archives

## When to choose
- you need automatic, no-user-input colorization of grayscale images
- you want a simple pretrained PyTorch model for image colorization
- you want to reproduce results from the Colorful Image Colorization paper

## When to avoid
- you need interactive or user-guided colorization with fine control (see the authors' interactive deep colorization work)
- you need training code or modern maintained tooling - the original Caffe branch is unsupported
- you require guaranteed accurate colors rather than plausible hallucinated ones

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, computer-vision, deep-learning
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python, cross-platform
- tags: colorization, grayscale-images, pytorch, pretrained-models, eccv-2016, caffe

## Member repositories
- richzhang/colorization (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:05.669336+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 2026-08-29T18:36:55.761269+00:00, confidence not recorded.
  - readme: https://github.com/richzhang/colorization (fetched 2026-08-28T04:08:05.669336+00:00, sha 4032175a2f5e)
  - homepage: http://richzhang.github.io/colorization/ (fetched 2026-08-29T09:31:02.596734+00:00, sha a20c0a9510a9)
- Data as of 2026-08-30T08:39:29.467469+00:00.