# msracver/Deep-Image-Analogy

The source code of 'Visual Attribute Transfer through Deep Image Analogy'.

Repository: https://github.com/msracver/Deep-Image-Analogy
Canonical: https://ross.abutalabs.com/products/deep-image-analogy
Homepage: https://arxiv.org/abs/1705.01088
Language: C++
License: MIT
License Family: permissive
Topics: style-transfer, deep-learning
Last push: 2021-09-27T04:52:35+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": 3390, "days_push": 1801, "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 1370, forks 230 (observed 2026-08-28T04:04:31.851315+00:00)

## What it is
Official C++/CUDA implementation of the SIGGRAPH 2017 'Visual Attribute Transfer through Deep Image Analogy' technique from Microsoft Research. It finds semantically meaningful dense correspondences between two images using CNN features to transfer color, texture, and style.

## Use cases
- transfer painting style to a photo
- swap styles between two artworks
- convert a sketch or painting into a photo
- perform color and style swap between images
- compute dense semantic correspondences between images
- texture transfer between images

## When to choose
- you need semantically-aware style transfer that respects image structure, not just global texture
- you want the reference implementation of the SIGGRAPH 2017 deep image analogy paper
- you have an NVIDIA GPU and a Windows environment with CUDA 7.5/8

## When to avoid
- you need a maintained cross-platform or Python-friendly tool - it is only tested on Windows with old CUDA versions
- your images are large - input is limited to roughly 700x500 pixels
- you want modern deep-learning style transfer with active community support

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, computer-vision, deep-learning
- domain: computer-vision, image-processing, deep-learning
- platform: windows, cpp
- tags: style-transfer, cuda, caffe, image-analogy, dense-correspondence, siggraph-2017, gpu

## Member repositories
- msracver/Deep-Image-Analogy (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:31.851315+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 2026-08-30T04:40:56.069468+00:00, confidence not recorded.
  - readme: https://github.com/msracver/Deep-Image-Analogy (fetched 2026-08-28T04:04:31.851315+00:00, sha bc4d4235c7bb)
  - homepage: https://arxiv.org/abs/1705.01088 (fetched 2026-08-29T11:57:42.760495+00:00, sha 596ff4cc4c19)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:57:42.764271+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:57:42.767677+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:57:42.769567+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:57:42.766011+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.