# luanfujun/deep-photo-styletransfer

Code and data for paper "Deep Photo Style Transfer": https://arxiv.org/abs/1703.07511

Repository: https://github.com/luanfujun/deep-photo-styletransfer
Canonical: https://ross.abutalabs.com/products/deep-photo-styletransfer
Language: MATLAB
License Family: other
Last push: 2021-08-02T01:07:44+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": 3451, "days_push": 1858, "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 9989, forks 1374 (observed 2026-08-28T04:10:39.182593+00:00)

## What it is
Reference implementation of the CVPR 2017 paper 'Deep Photo Style Transfer', performing photorealistic image style transfer using Torch with VGG-19 and matting Laplacian-based color constraints. It is research code combining Lua/Torch scripts with MATLAB/Octave preprocessing steps.

## Use cases
- transfer the style of one photo onto another photorealistically
- reproduce results from the Deep Photo Style Transfer paper
- apply artistic style to a photo while preserving image structure
- experiment with neural style transfer using segmentation masks
- run GPU-accelerated deep image stylization locally

## When to choose
- you need photorealistic (not painterly) style transfer with content preserved
- you want the exact reference implementation of the paper for research
- you can work with Torch7 and MATLAB/Octave tooling

## When to avoid
- you want a maintained, easy-to-install modern framework (Torch7 is deprecated)
- you need a commercial license - it is academic/non-commercial use only
- you prefer PyTorch or TensorFlow pipelines
- you need Windows or macOS support out of the box

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, deep-learning, machine-learning
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python, cpp
- tags: style-transfer, neural-style, torch7, matlab, research-code, vgg-19, photographic-style-transfer, academic-use-only, linux, gpu

## Member repositories
- luanfujun/deep-photo-styletransfer (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:39.182593+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 2026-08-29T17:20:01.609343+00:00, confidence not recorded.
  - readme: https://github.com/luanfujun/deep-photo-styletransfer (fetched 2026-08-28T04:10:39.182593+00:00, sha 138f8b5861a1)
- Data as of 2026-08-30T08:39:29.467469+00:00.