idealo/image-super-resolution

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

Archived
49
/ 100
Emerging

Keras-based implementation of Residual Dense Networks (RDN/RRDN) for single-image super-resolution, supporting both PSNR-driven and adversarial training with perceptual loss via VGG19 feature extraction. Includes pre-trained models for different use cases (standard upscaling, artifact cancellation, photo-realistic GAN output) and handles large images through patch-based inference to avoid memory constraints. Provides Docker and AWS cloud training pipelines alongside Jupyter notebooks for rapid experimentation.

4,817 stars. No commits in the last 6 months.

Archived Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

4,817

Forks

779

Language

Python

License

Apache-2.0

Last pushed

Dec 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/idealo/image-super-resolution"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.