# idealo/image-super-resolution

🔎 Super-scale your images and run experiments with Residual Dense and Adversarial Networks.

Repository: https://github.com/idealo/image-super-resolution
Canonical: https://ross.abutalabs.com/products/image-super-resolution
Homepage: https://idealo.github.io/image-super-resolution/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: image-super-resolution, neural-network, tensorflow, keras, aws, convolutional-neural-networks, deep-learning, computer-vision, machine-learning, e-commerce, idealo, docker, nvidia-docker, image-processing, super-resolution
Archived: true
Last push: 2024-12-18T16:08:09+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2837, "days_push": 623, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4818, forks 765 (observed 2026-08-28T04:09:00.450759+00:00)

## What it is
A Python library providing Keras implementations of Residual Dense and Adversarial Networks for single image super-resolution, including pre-trained models and training scripts. It supports upscaling low-resolution images and training custom models with content and adversarial loss, with Docker and AWS tooling.

## Use cases
- upscale low resolution images
- enhance quality of small photos with deep learning
- train a super-resolution GAN model
- apply pre-trained ESRGAN/RDN models to images
- run super-resolution experiments on AWS with nvidia-docker
- extract deep features with VGG19 for perceptual loss

## When to choose
- you need neural-network-based image upscaling in Python with Keras/TensorFlow
- you want pre-trained RDN or ESRGAN-style models ready to use
- you want to experiment with training super-resolution networks with GAN and perceptual losses

## When to avoid
- you need actively maintained software (the repo was archived in January 2025)
- you need modern TensorFlow/Keras versions or Python beyond 3.6 compatibility
- you need video super-resolution or non-image modalities

## Facets
- artifact type: library
- maturity: abandoned
- function: image-processing, machine-learning, deep-learning
- domain: image-processing, computer-vision, machine-learning, deep-learning
- platform: python, cross-platform
- tags: super-resolution, keras, tensorflow, gan, residual-dense-network, esrgan, image-upscaling, aws, pretrained-models, docker, gpu

## Member repositories
- idealo/image-super-resolution (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:00.450759+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 2026-08-29T18:18:33.655290+00:00, confidence not recorded.
  - readme: https://github.com/idealo/image-super-resolution (fetched 2026-08-28T04:09:00.450759+00:00, sha 9080a15e9a70)
  - homepage: https://idealo.github.io/image-super-resolution/ (fetched 2026-08-29T09:01:27.714226+00:00, sha 738d16373bc4)
- Data as of 2026-08-30T08:39:29.467469+00:00.