# isl-org/PhotorealismEnhancement

Code & Data for Enhancing Photorealism Enhancement

Repository: https://github.com/isl-org/PhotorealismEnhancement
Canonical: https://ross.abutalabs.com/products/photorealismenhancement
Language: Python
License Family: other
Archived: true
Last push: 2024-09-02T19:26:44+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1941, "days_push": 730, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1335, forks 108 (observed 2026-08-28T04:04:25.246241+00:00)

## What it is
Research code and data from Intel Labs for the paper 'Enhancing Photorealism Enhancement', a neural network that makes rendered images (e.g., from GTA) look photorealistic. Intel has officially discontinued the project and no longer maintains it.

## Use cases
- make game renders look like real photos
- translate synthetic images to photorealistic ones
- reproduce the Enhancing Photorealism Enhancement paper
- sim2real image translation for driving datasets
- compare image-to-image translation baselines like CUT and MUNIT

## When to choose
- you need the exact models and data from the EPE paper for research reproduction
- you want to study photorealistic image-to-image translation on driving scenes
- you're willing to fork and maintain the code yourself

## When to avoid
- you need maintained software with bug fixes or support
- you want a production-ready image enhancement tool
- you cannot work with research-grade Python code and GPU training pipelines

## Facets
- artifact type: library
- maturity: abandoned
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, artificial-intelligence
- platform: python
- tags: photorealism, image-to-image-translation, gans, sim2real, research-code, intel, discontinued, linux, gpu

## Member repositories
- isl-org/PhotorealismEnhancement (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:25.246241+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 2026-08-30T04:44:22.537529+00:00, confidence not recorded.
  - readme: https://github.com/isl-org/PhotorealismEnhancement (fetched 2026-08-28T04:04:25.246241+00:00, sha 24d4f2a7d389)
- Data as of 2026-08-30T08:39:29.467469+00:00.