idealo/image-super-resolution

Health v2 · maintenance only

Flags: archived

Adoption not part of the score

4818 stars · 765 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity abandoned

image-processing machine-learning deep-learning image-processing computer-vision machine-learning deep-learning python cross-platform super-resolution keras tensorflow gan residual-dense-network esrgan image-upscaling aws pretrained-models docker gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="idealo/image-super-resolution")