megvii-research/DCLS-SR

Official PyTorch implementation of the paper "Deep Constrained Least Squares for Blind Image Super-Resolution", CVPR 2022.

39
/ 100
Emerging

This helps image restoration specialists and visual content creators enhance blurry, low-resolution images by predicting the missing details. You provide a poor-quality image, and it outputs a significantly sharper, higher-resolution version, even when the original blur is complex or unknown. It's designed for professionals who need to improve image clarity for analysis or display.

238 stars. No commits in the last 6 months.

Use this if you need to reliably upscale and deblur images where the blur type is unknown, making them clearer for tasks like forensic analysis, old photo restoration, or visual content improvement.

Not ideal if you're looking for a simple drag-and-drop tool without any technical setup, as this requires some programming environment knowledge.

image-enhancement photo-restoration digital-forensics visual-content-creation remote-sensing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

238

Forks

21

Language

Python

License

MIT

Last pushed

May 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/megvii-research/DCLS-SR"

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