# aiff22/DPED

Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks

Repository: https://github.com/aiff22/DPED
Canonical: https://ross.abutalabs.com/products/dped
Language: Python
License Family: other
Topics: image-enhancement, image-processing, computer-vision, deep-learning, dped, gan, convolutional-neural-networks, generative-adversarial-networks
Last push: 2025-08-23T13:24:16+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 38, release rhythm 35, longevity 100
- inputs: {"age_days": 3297, "days_push": 375, "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 1710, forks 366 (observed 2026-08-28T04:05:25.641270+00:00)

## What it is
DPED is a Python/TensorFlow implementation of a deep convolutional network approach that translates ordinary smartphone photos into DSLR-quality images, based on the ICCV 2017 paper of the same name. It includes training scripts, pre-trained models for iPhone, BlackBerry, and Sony photos, and the DPED dataset of paired photo patches.

## Use cases
- enhance smartphone photos to DSLR quality automatically
- train a GAN for photo quality enhancement
- apply pre-trained image enhancement models to arbitrary-resolution photos
- research image-to-image translation with adversarial losses
- improve color and texture of mobile camera photos

## When to choose
- you want to enhance mobile photos with a proven deep learning model
- you need a research baseline for photo enhancement with GANs
- you want to train custom enhancement models on the DPED dataset

## When to avoid
- you need a maintained production library with a license
- you cannot use an Nvidia GPU or TensorFlow 1.x/2.x
- you need RAW photo enhancement or bokeh effects (see PyNET projects instead)

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning, photography
- platform: python, cross-platform
- tags: photo-enhancement, gan, image-to-image-translation, cnn, tensorflow, dped-dataset, research-code, gpu, linux

## Member repositories
- aiff22/DPED (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:25.641270+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 2026-08-30T03:35:03.646471+00:00, confidence not recorded.
  - readme: https://github.com/aiff22/DPED (fetched 2026-08-28T04:05:25.641270+00:00, sha 153a8799f0c4)
- Data as of 2026-08-30T08:39:29.467469+00:00.