# satoshiiizuka/siggraph2016_colorization

Code for the paper 'Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification'.

Repository: https://github.com/satoshiiizuka/siggraph2016_colorization
Canonical: https://ross.abutalabs.com/products/siggraph2016_colorization
Homepage: http://hi.cs.waseda.ac.jp/~iizuka/projects/colorization/
Language: Lua
License: NOASSERTION
License Family: other
Last push: 2022-06-13T02:05:02+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3787, "days_push": 1543, "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 2142, forks 294 (observed 2026-08-28T04:06:18.506559+00:00)

## What it is
A Torch7 implementation of the SIGGRAPH 2016 paper 'Let there be Color!' that automatically colorizes grayscale images using a deep network combining global and local image priors. It ships as a Lua script with a pretrained model trained on the Places dataset.

## Use cases
- colorize old black and white photos
- automatically add color to grayscale images
- restore color to historical photographs
- convert monochrome images to realistic color
- research baseline for image colorization

## When to choose
- you need automatic colorization of grayscale photos, especially natural outdoor scenes
- you want to reproduce or build on the SIGGRAPH 2016 colorization paper
- you have a Torch7 environment available

## When to avoid
- you need a maintained tool with modern framework support (Torch7 is deprecated)
- you need commercial use (CC BY-NC-SA license)
- you need reliable colorization of large images or non-natural scenes

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, computer-vision, artificial-intelligence
- platform: cli
- tags: colorization, torch7, research-code, grayscale-to-color, siggraph-2016, linux, macos

## Member repositories
- satoshiiizuka/siggraph2016_colorization (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:18.506559+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 2026-08-30T02:51:17.348874+00:00, confidence not recorded.
  - readme: https://github.com/satoshiiizuka/siggraph2016_colorization (fetched 2026-08-28T04:06:18.506559+00:00, sha bc50094b0e5e)
- Data as of 2026-08-30T08:39:29.467469+00:00.