# junyanz/interactive-deep-colorization

Deep learning software for colorizing black and white images with a few clicks.

Repository: https://github.com/junyanz/interactive-deep-colorization
Canonical: https://ross.abutalabs.com/products/interactive-deep-colorization
Homepage: https://richzhang.github.io/ideepcolor/
Language: Python
License: MIT
License Family: permissive
Topics: colorization, automatic-colorization, deep-learning, deep-learning-algorithms, computer-vision, caffe, interactive
Last push: 2022-07-29T10:15:32+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": 3404, "days_push": 1496, "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 2692, forks 446 (observed 2026-08-28T04:07:11.054186+00:00)

## What it is
A deep learning application for interactively colorizing black and white images with user-guided hints, based on the SIGGRAPH 2017 paper 'Real-Time User-Guided Image Colorization with Learned Deep Priors'. It provides both a full Qt GUI demo and a barebones iPython notebook demo, with Caffe and PyTorch backends.

## Use cases
- colorize black and white photos with a few clicks
- add color hints to grayscale images interactively
- restore color to old family photographs
- experiment with user-guided deep colorization models
- run the local hints network colorization demo
- try global hints based image colorization

## When to choose
- you need interactive, user-guided colorization rather than fully automatic colorization
- you want to reproduce or build on the SIGGRAPH 2017 colorization research
- you have a CUDA GPU or are okay with slower CPU inference
- you want a research-grade tool with both GUI and notebook interfaces

## When to avoid
- you need a maintained production tool with modern dependency support
- you want fully automatic batch colorization without user hints
- you cannot install legacy Caffe or old PyTorch versions
- you need a simple library API rather than a demo application

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning, gui
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: windows, python
- tags: colorization, interactive, caffe, pytorch, research, siggraph, user-guided-colorization, linux, macos, gpu

## Member repositories
- junyanz/interactive-deep-colorization (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:11.054186+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 2026-08-30T02:16:32.139233+00:00, confidence not recorded.
  - readme: https://github.com/junyanz/interactive-deep-colorization (fetched 2026-08-28T04:07:11.054186+00:00, sha cc2c71de409f)
- Data as of 2026-08-30T08:39:29.467469+00:00.